├── .flake8 ├── .git-blame-ignore-revs ├── .github ├── scripts │ ├── .gitignore │ ├── aishell │ │ └── ASR │ │ │ └── run.sh │ ├── audioset │ │ └── AT │ │ │ └── run.sh │ ├── baker_zh │ │ └── TTS │ │ │ └── run-matcha.sh │ ├── compute-fbank-librispeech-test-clean-and-test-other.sh │ ├── docker │ │ ├── Dockerfile │ │ └── generate_build_matrix.py │ ├── download-gigaspeech-dev-test-dataset.sh │ ├── download-librispeech-test-clean-and-test-other-dataset.sh │ ├── generate-piper-phonemize-page.py │ ├── install-kaldifeat.sh │ ├── ksponspeech │ │ └── ASR │ │ │ └── run.sh │ ├── librispeech │ │ └── ASR │ │ │ ├── run.sh │ │ │ └── run_rknn.sh │ ├── ljspeech │ │ └── TTS │ │ │ ├── run-matcha.sh │ │ │ └── run.sh │ ├── multi-zh-hans.sh │ ├── prepare-librispeech-test-clean-and-test-other-manifests.sh │ ├── run-gigaspeech-pruned-transducer-stateless2-2022-05-12.sh │ ├── run-gigaspeech-zipformer-2023-10-17.sh │ ├── run-librispeech-lstm-transducer-stateless2-2022-09-03.sh │ ├── run-multi-corpora-zipformer.sh │ ├── run-swbd-conformer-ctc-2023-08-26.sh │ ├── run-wenetspeech-pruned-transducer-stateless2.sh │ ├── test-ncnn-export.sh │ ├── test-onnx-export.sh │ └── yesno │ │ └── ASR │ │ └── run.sh └── workflows │ ├── aishell.yml │ ├── audioset.yml │ ├── baker_zh.yml │ ├── build-cpu-docker.yml │ ├── build-doc.yml │ ├── build-docker-image.yml │ ├── ksponspeech.yml │ ├── librispeech.yml │ ├── ljspeech.yml │ ├── multi-zh-hans.yml │ ├── rknn.yml │ ├── run-docker-image.yml │ ├── run-gigaspeech-2022-05-13.yml │ ├── run-gigaspeech-zipformer-2023-10-17.yml │ ├── run-librispeech-lstm-transducer-stateless2-2022-09-03.yml │ ├── run-multi-corpora-zipformer.yml │ ├── run-ptb-rnn-lm.yml │ ├── run-swbd-conformer-ctc.yml │ ├── run-wenetspeech-pruned-transducer-stateless2.yml │ ├── style_check.yml │ ├── test-ncnn-export.yml │ ├── test-onnx-export.yml │ ├── test.yml │ └── yesno.yml ├── .gitignore ├── .pre-commit-config.yaml ├── LICENSE ├── README.md ├── contributing.md ├── docker ├── README.md ├── Ubuntu18.04-pytorch1.12.1-cuda11.3-cudnn8 │ └── Dockerfile ├── Ubuntu18.04-pytorch1.7.1-cuda11.0-cudnn8 │ └── Dockerfile ├── torch1.12.1-cuda11.3.dockerfile ├── torch1.13.0-cuda11.6.dockerfile ├── torch1.9.0-cuda10.2.dockerfile ├── torch2.0.0-cuda11.7.dockerfile ├── torch2.1.0-cuda11.8.dockerfile ├── torch2.1.0-cuda12.1.dockerfile ├── torch2.2.0-cuda11.8.dockerfile ├── torch2.2.0-cuda12.1.dockerfile ├── torch2.2.1-cuda11.8.dockerfile ├── torch2.2.1-cuda12.1.dockerfile ├── torch2.2.2-cuda11.8.dockerfile ├── torch2.2.2-cuda12.1.dockerfile ├── torch2.3.1-cuda11.8.dockerfile ├── torch2.3.1-cuda12.1.dockerfile ├── torch2.4.0-cuda11.8.dockerfile ├── torch2.4.0-cuda12.1.dockerfile ├── torch2.4.0-cuda12.4.dockerfile ├── torch2.4.1-cuda11.8.dockerfile ├── torch2.4.1-cuda12.1.dockerfile └── torch2.4.1-cuda12.4.dockerfile ├── docs ├── .gitignore ├── Makefile ├── README.md ├── make.bat ├── requirements.txt └── source │ ├── _static │ ├── kaldi-align │ │ ├── Lab41-SRI-VOiCES-src-sp0307-ch127535-sg0042.wav │ │ ├── at.wav │ │ ├── beside.wav │ │ ├── curiosity.wav │ │ ├── had.wav │ │ ├── i.wav │ │ ├── me.wav │ │ ├── moment.wav │ │ ├── that.wav │ │ └── this.wav │ └── logo.png │ ├── conf.py │ ├── contributing │ ├── code-style.rst │ ├── doc.rst │ ├── how-to-create-a-recipe.rst │ ├── images │ │ ├── doc-contrib.png │ │ ├── pre-commit-check-success.png │ │ └── pre-commit-check.png │ └── index.rst │ ├── decoding-with-langugage-models │ ├── LODR.rst │ ├── index.rst │ ├── rescoring.rst │ └── shallow-fusion.rst │ ├── docker │ ├── img │ │ └── docker-hub.png │ ├── index.rst │ └── intro.rst │ ├── faqs.rst │ ├── for-dummies │ ├── data-preparation.rst │ ├── decoding.rst │ ├── environment-setup.rst │ ├── index.rst │ ├── model-export.rst │ └── training.rst │ ├── fst-based-forced-alignment │ ├── diff.rst │ ├── index.rst │ ├── k2-based.rst │ └── kaldi-based.rst │ ├── huggingface │ ├── index.rst │ ├── pic │ │ ├── hugging-face-sherpa-2.png │ │ ├── hugging-face-sherpa-3.png │ │ └── hugging-face-sherpa.png │ ├── pretrained-models.rst │ └── spaces.rst │ ├── index.rst │ ├── installation │ ├── images │ │ ├── README.md │ │ ├── device-CPU_CUDA-orange.svg │ │ ├── k2-gt-v1.9-blueviolet.svg │ │ ├── os-Linux_macOS-ff69b4.svg │ │ ├── python-gt-v3.6-blue.svg │ │ └── torch-gt-v1.6.0-green.svg │ └── index.rst │ ├── model-export │ ├── code │ │ ├── export-conv-emformer-transducer-for-ncnn-output.txt │ │ ├── export-lstm-transducer-for-ncnn-output.txt │ │ ├── export-model-state-dict-pretrained-out.txt │ │ ├── export-zipformer-transducer-for-ncnn-output.txt │ │ ├── generate-int-8-scale-table-for-conv-emformer.txt │ │ ├── generate-int-8-scale-table-for-lstm.txt │ │ ├── test-streaming-ncnn-decode-conv-emformer-transducer-libri.txt │ │ ├── test-streaming-ncnn-decode-lstm-transducer-libri.txt │ │ └── test-streaming-ncnn-decode-zipformer-transducer-libri.txt │ ├── export-model-state-dict.rst │ ├── export-ncnn-conv-emformer.rst │ ├── export-ncnn-lstm.rst │ ├── export-ncnn-zipformer.rst │ ├── export-ncnn.rst │ ├── export-onnx.rst │ ├── export-with-torch-jit-script.rst │ ├── export-with-torch-jit-trace.rst │ └── index.rst │ └── recipes │ ├── Finetune │ ├── adapter │ │ └── finetune_adapter.rst │ ├── from_supervised │ │ └── finetune_zipformer.rst │ └── index.rst │ ├── Non-streaming-ASR │ ├── aishell │ │ ├── conformer_ctc.rst │ │ ├── images │ │ │ ├── aishell-conformer-ctc-tensorboard-log.jpg │ │ │ ├── aishell-tdnn-lstm-ctc-tensorboard-log.jpg │ │ │ └── aishell-transducer_stateless_modified-tensorboard-log.png │ │ ├── index.rst │ │ ├── stateless_transducer.rst │ │ └── tdnn_lstm_ctc.rst │ ├── index.rst │ ├── librispeech │ │ ├── conformer_ctc.rst │ │ ├── distillation.rst │ │ ├── images │ │ │ ├── distillation_codebook.png │ │ │ ├── distillation_directory.png │ │ │ ├── librispeech-conformer-ctc-tensorboard-log.png │ │ │ └── librispeech-pruned-transducer-tensorboard-log.jpg │ │ ├── index.rst │ │ ├── pruned_transducer_stateless.rst │ │ ├── tdnn_lstm_ctc.rst │ │ ├── zipformer_ctc_blankskip.rst │ │ └── zipformer_mmi.rst │ ├── timit │ │ ├── index.rst │ │ ├── tdnn_ligru_ctc.rst │ │ └── tdnn_lstm_ctc.rst │ └── yesno │ │ ├── images │ │ └── tdnn-tensorboard-log.png │ │ ├── index.rst │ │ └── tdnn.rst │ ├── RNN-LM │ ├── index.rst │ └── librispeech │ │ └── lm-training.rst │ ├── Streaming-ASR │ ├── index.rst │ ├── introduction.rst │ └── librispeech │ │ ├── images │ │ ├── librispeech-lstm-transducer-tensorboard-log.png │ │ └── streaming-librispeech-pruned-transducer-tensorboard-log.jpg │ │ ├── index.rst │ │ ├── lstm_pruned_stateless_transducer.rst │ │ ├── pruned_transducer_stateless.rst │ │ └── zipformer_transducer.rst │ ├── TTS │ ├── index.rst │ ├── ljspeech │ │ └── vits.rst │ └── vctk │ │ └── vits.rst │ └── index.rst ├── egs ├── aidatatang_200zh │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── __init__.py │ │ ├── compute_fbank_aidatatang_200zh.py │ │ ├── compute_fbank_musan.py │ │ ├── display_manifest_statistics.py │ │ ├── prepare_char.py │ │ ├── prepare_lang.py │ │ ├── prepare_words.py │ │ ├── test_prepare_lang.py │ │ └── text2token.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless2 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── lstmp.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ └── train.py │ │ └── shared ├── aishell │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── conformer_ctc │ │ ├── README.md │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── export.py │ │ ├── jit_pretrained_decode_with_H.py │ │ ├── jit_pretrained_decode_with_HL.py │ │ ├── jit_pretrained_decode_with_HLG.py │ │ ├── label_smoothing.py │ │ ├── pretrained.py │ │ ├── subsampling.py │ │ ├── test_subsampling.py │ │ ├── test_transformer.py │ │ ├── train.py │ │ └── transformer.py │ │ ├── conformer_mmi │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── label_smoothing.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── transformer.py │ │ ├── local │ │ ├── __init__.py │ │ ├── compile_hlg.py │ │ ├── compile_lg.py │ │ ├── compute_fbank_aidatatang_200zh.py │ │ ├── compute_fbank_aishell.py │ │ ├── compute_fbank_musan.py │ │ ├── convert_transcript_words_to_tokens.py │ │ ├── display_manifest_statistics.py │ │ ├── generate_unique_lexicon.py │ │ ├── prepare_char.py │ │ ├── prepare_char_lm_training_data.py │ │ ├── prepare_lang.py │ │ ├── prepare_lang_bbpe.py │ │ ├── prepare_lang_fst.py │ │ ├── sort_lm_training_data.py │ │ ├── test_prepare_lang.py │ │ └── train_bbpe_model.py │ │ ├── prepare.sh │ │ ├── prepare_aidatatang_200zh.sh │ │ ├── pruned_transducer_stateless2 │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ └── train.py │ │ ├── pruned_transducer_stateless3 │ │ ├── aidatatang_200zh.py │ │ ├── aishell.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── lstmp.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ └── train.py │ │ ├── pruned_transducer_stateless7 │ │ ├── aishell.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── decoder2.py │ │ ├── do_not_use_it_directly.py │ │ ├── encoder_interface.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── jit_pretrained.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── onnx_check.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── train.py │ │ └── zipformer.py │ │ ├── pruned_transducer_stateless7_bbpe │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── jit_pretrained.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── test_model.py │ │ ├── train.py │ │ └── zipformer.py │ │ ├── pruned_transducer_stateless7_streaming │ │ ├── README.md │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── do_not_use_it_directly.py │ │ ├── encoder_interface.py │ │ ├── export-for-ncnn-zh.py │ │ ├── export-for-ncnn.py │ │ ├── export-onnx-zh.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── jit_pretrained.py │ │ ├── jit_trace_export.py │ │ ├── jit_trace_pretrained.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── ncnn_custom_layer.py │ │ ├── onnx_check.py │ │ ├── onnx_model_wrapper.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming-ncnn-decode.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── test_model.py │ │ ├── train.py │ │ ├── zipformer.py │ │ └── zipformer_for_ncnn_export_only.py │ │ ├── shared │ │ ├── tdnn_lstm_ctc │ │ ├── README.md │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── decode.py │ │ ├── model.py │ │ ├── pretrained.py │ │ └── train.py │ │ ├── transducer_stateless │ │ ├── README.md │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── pretrained.py │ │ ├── subsampling.py │ │ ├── test_decoder.py │ │ ├── train.py │ │ └── transformer.py │ │ ├── transducer_stateless_modified-2 │ │ ├── README.md │ │ ├── __init__.py │ │ ├── aidatatang_200zh.py │ │ ├── aishell.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── pretrained.py │ │ ├── subsampling.py │ │ ├── test_decoder.py │ │ ├── train.py │ │ └── transformer.py │ │ ├── transducer_stateless_modified │ │ ├── README.md │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── pretrained.py │ │ ├── subsampling.py │ │ ├── test_decoder.py │ │ ├── train.py │ │ └── transformer.py │ │ ├── whisper │ │ ├── asr_datamodule.py │ │ ├── decode.py │ │ ├── ds_config_zero1.json │ │ ├── label_smoothing.py │ │ ├── optim.py │ │ ├── requirements.txt │ │ ├── train.py │ │ └── whisper_encoder_forward_monkey_patch.py │ │ └── zipformer │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decode_bbpe.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx-streaming.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── jit_pretrained.py │ │ ├── jit_pretrained_bbpe.py │ │ ├── jit_pretrained_streaming.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── onnx_check.py │ │ ├── onnx_decode.py │ │ ├── onnx_pretrained-streaming.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── pretrained_bbpe.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── subsampling.py │ │ ├── train.py │ │ ├── train_bbpe.py │ │ └── zipformer.py ├── aishell2 │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── __init__.py │ │ ├── compile_lg.py │ │ ├── compute_fbank_aishell2.py │ │ ├── compute_fbank_musan.py │ │ ├── display_manifest_statistics.py │ │ ├── prepare_char.py │ │ ├── prepare_lang.py │ │ ├── prepare_words.py │ │ ├── text2segments.py │ │ └── text2token.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless5 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ └── train.py │ │ └── shared ├── aishell4 │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── __init__.py │ │ ├── compute_fbank_aishell4.py │ │ ├── compute_fbank_musan.py │ │ ├── display_manifest_statistics.py │ │ ├── prepare_char.py │ │ ├── prepare_lang.py │ │ ├── prepare_words.py │ │ ├── test_prepare_lang.py │ │ ├── text2segments.py │ │ ├── text2token.py │ │ └── text_normalize.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless5 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── local │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── test_model.py │ │ └── train.py │ │ └── shared ├── alimeeting │ ├── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ │ ├── __init__.py │ │ │ ├── compute_fbank_alimeeting.py │ │ │ ├── compute_fbank_musan.py │ │ │ ├── display_manifest_statistics.py │ │ │ ├── prepare_char.py │ │ │ ├── prepare_lang.py │ │ │ ├── prepare_words.py │ │ │ ├── test_prepare_lang.py │ │ │ ├── text2segments.py │ │ │ └── text2token.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless2 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ └── train.py │ │ └── shared │ └── ASR_v2 │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── __init__.py │ │ ├── compute_fbank_alimeeting.py │ │ ├── compute_fbank_musan.py │ │ ├── prepare_alimeeting_enhanced.py │ │ ├── prepare_alimeeting_gss.sh │ │ ├── prepare_char.py │ │ ├── prepare_words.py │ │ ├── text2segments.py │ │ └── text2token.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless7 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── jit_pretrained.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── test_model.py │ │ ├── train.py │ │ └── zipformer.py │ │ └── shared ├── ami │ ├── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ │ ├── __init__.py │ │ │ ├── compute_fbank_ami.py │ │ │ ├── compute_fbank_musan.py │ │ │ ├── prepare_ami_enhanced.py │ │ │ ├── prepare_ami_gss.sh │ │ │ ├── prepare_lang_bpe.py │ │ │ └── train_bpe_model.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless7 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ │ └── shared │ └── SURT │ │ ├── README.md │ │ ├── dprnn_zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── dprnn.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── test_model.py │ │ ├── train.py │ │ ├── train_adapt.py │ │ └── zipformer.py │ │ ├── local │ │ ├── add_source_feats.py │ │ ├── compute_fbank_aimix.py │ │ ├── compute_fbank_ami.py │ │ ├── compute_fbank_icsi.py │ │ ├── compute_fbank_ihm.py │ │ ├── prepare_ami_train_cuts.py │ │ ├── prepare_icsi_train_cuts.py │ │ ├── prepare_lang_bpe.py │ │ └── train_bpe_model.py │ │ ├── prepare.sh │ │ └── shared ├── audioset │ └── AT │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── compute_fbank_musan.py │ │ ├── compute_weight.py │ │ └── generate_audioset_manifest.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── zipformer │ │ ├── at_datamodule.py │ │ ├── encoder_interface.py │ │ ├── evaluate.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── jit_pretrained.py │ │ ├── model.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── zipformer.py ├── baker_zh │ └── TTS │ │ ├── .gitignore │ │ ├── README.md │ │ ├── local │ │ ├── audio.py │ │ ├── compute_fbank_baker_zh.py │ │ ├── compute_fbank_statistics.py │ │ ├── convert_text_to_tokens.py │ │ ├── fbank.py │ │ ├── generate_tokens.py │ │ └── validate_manifest.py │ │ ├── matcha │ │ ├── __init__.py │ │ ├── audio.py │ │ ├── export_onnx.py │ │ ├── export_onnx_hifigan.py │ │ ├── fbank.py │ │ ├── generate_lexicon.py │ │ ├── hifigan │ │ ├── infer.py │ │ ├── model.py │ │ ├── models │ │ ├── monotonic_align │ │ ├── onnx_pretrained.py │ │ ├── tokenizer.py │ │ ├── train.py │ │ ├── tts_datamodule.py │ │ └── utils.py │ │ ├── prepare.sh │ │ └── shared ├── commonvoice │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── compile_hlg.py │ │ ├── compile_lg.py │ │ ├── compute_fbank_commonvoice_dev_test.py │ │ ├── compute_fbank_commonvoice_splits.py │ │ ├── compute_fbank_musan.py │ │ ├── filter_cuts.py │ │ ├── prepare_char.py │ │ ├── prepare_lang.py │ │ ├── prepare_lang_bpe.py │ │ ├── prepare_lang_fst.py │ │ ├── preprocess_commonvoice.py │ │ ├── train_bpe_model.py │ │ ├── validate_bpe_lexicon.py │ │ └── word_segment_yue.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless7 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── onnx_check.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── train.py │ │ └── zipformer.py │ │ ├── pruned_transducer_stateless7_streaming │ │ ├── README.md │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── do_not_use_it_directly.py │ │ ├── encoder_interface.py │ │ ├── export-for-ncnn-zh.py │ │ ├── export-for-ncnn.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── finetune.py │ │ ├── generate_model_from_checkpoint.py │ │ ├── jit_pretrained.py │ │ ├── jit_trace_export.py │ │ ├── jit_trace_pretrained.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── onnx_check.py │ │ ├── onnx_model_wrapper.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming-ncnn-decode.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── test_model.py │ │ ├── train.py │ │ ├── zipformer.py │ │ └── zipformer_for_ncnn_export_only.py │ │ ├── shared │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decode_char.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx-ctc.py │ │ ├── export-onnx-streaming-ctc.py │ │ ├── export-onnx-streaming.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── onnx_check.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── streaming_decode_char.py │ │ ├── subsampling.py │ │ ├── train.py │ │ ├── train_char.py │ │ └── zipformer.py ├── csj │ └── ASR │ │ ├── .gitignore │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── add_transcript_mode.py │ │ ├── compute_fbank_csj.py │ │ ├── compute_fbank_musan.py │ │ ├── conf │ │ │ ├── disfluent.ini │ │ │ ├── fluent.ini │ │ │ ├── number.ini │ │ │ └── symbol.ini │ │ ├── disfluent_recogs_to_fluent.py │ │ ├── display_manifest_statistics.py │ │ ├── prepare_lang_char.py │ │ ├── utils │ │ │ ├── asr_datamodule.py │ │ │ └── tokenizer.py │ │ └── validate_manifest.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless7_streaming │ │ ├── TelegramStreamIO.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── do_not_use_it_directly.py │ │ ├── encoder_interface.py │ │ ├── export-for-ncnn.py │ │ ├── export.py │ │ ├── jit_trace_export.py │ │ ├── jit_trace_pretrained.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming-ncnn-decode.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── test_model.py │ │ ├── tokenizer.py │ │ ├── train.py │ │ ├── zipformer.py │ │ └── zipformer_for_ncnn_export_only.py │ │ └── shared ├── fluent_speech_commands │ └── SLU │ │ ├── README.md │ │ ├── local │ │ ├── compile_hlg.py │ │ ├── compute_fbank_slu.py │ │ ├── generate_lexicon.py │ │ └── prepare_lang.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── transducer │ │ ├── __init__.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── slu_datamodule.py │ │ ├── subsampling.py │ │ ├── test_conformer.py │ │ ├── test_decoder.py │ │ ├── test_joiner.py │ │ ├── test_transducer.py │ │ ├── train.py │ │ └── transformer.py ├── gigaspeech │ ├── ASR │ │ ├── .gitignore │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── conformer_ctc │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── gigaspeech_scoring.py │ │ │ ├── label_smoothing.py │ │ │ ├── subsampling.py │ │ │ ├── train.py │ │ │ └── transformer.py │ │ ├── local │ │ │ ├── __init__.py │ │ │ ├── compile_hlg.py │ │ │ ├── compute_fbank_gigaspeech.py │ │ │ ├── compute_fbank_gigaspeech_splits.py │ │ │ ├── compute_fbank_musan.py │ │ │ ├── convert_transcript_words_to_tokens.py │ │ │ ├── generate_unique_lexicon.py │ │ │ ├── prepare_lang.py │ │ │ ├── prepare_lang_bpe.py │ │ │ ├── preprocess_gigaspeech.py │ │ │ └── train_bpe_model.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless2 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── compute_ppl.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── gigaspeech_scoring.py │ │ │ ├── joiner.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ └── train.py │ │ ├── shared │ │ └── zipformer │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── ctc_decode.py │ │ │ ├── decode.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx-ctc.py │ │ │ ├── export-onnx-streaming.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── gigaspeech_scoring.py │ │ │ ├── jit_pretrained.py │ │ │ ├── jit_pretrained_ctc.py │ │ │ ├── jit_pretrained_streaming.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── my_profile.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_decode.py │ │ │ ├── onnx_pretrained-streaming.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── onnx_pretrained_ctc.py │ │ │ ├── onnx_pretrained_ctc_H.py │ │ │ ├── onnx_pretrained_ctc_HL.py │ │ │ ├── onnx_pretrained_ctc_HLG.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── pretrained_ctc.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── subsampling.py │ │ │ ├── test_scaling.py │ │ │ ├── test_subsampling.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ └── KWS │ │ ├── RESULTS.md │ │ ├── prepare.sh │ │ ├── run.sh │ │ ├── shared │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode-asr.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx-streaming.py │ │ ├── export.py │ │ ├── finetune.py │ │ ├── gigaspeech_scoring.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── scaling.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── zipformer.py ├── ksponspeech │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── compute_fbank_ksponspeech.py │ │ ├── compute_fbank_musan.py │ │ ├── filter_cuts.py │ │ ├── train_bpe_model.py │ │ └── validate_manifest.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless7_streaming │ │ ├── README.md │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── onnx_check.py │ │ ├── onnx_model_wrapper.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── test_model.py │ │ ├── train.py │ │ └── zipformer.py │ │ ├── shared │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── ctc_decode.py │ │ ├── decode.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx-ctc.py │ │ ├── export-onnx-streaming-ctc.py │ │ ├── export-onnx-streaming.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── generate_averaged_model.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── onnx_check.py │ │ ├── onnx_decode.py │ │ ├── onnx_pretrained-streaming-ctc.py │ │ ├── onnx_pretrained-streaming.py │ │ ├── onnx_pretrained.py │ │ ├── onnx_pretrained_ctc.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── pretrained_ctc.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── subsampling.py │ │ ├── test_scaling.py │ │ ├── test_subsampling.py │ │ ├── train.py │ │ └── zipformer.py ├── libricss │ └── SURT │ │ ├── README.md │ │ ├── dprnn_zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── dprnn.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── train.py │ │ ├── train_adapt.py │ │ └── zipformer.py │ │ ├── heat.png │ │ ├── local │ │ ├── add_source_feats.py │ │ ├── compute_fbank_libricss.py │ │ ├── compute_fbank_librispeech.py │ │ ├── compute_fbank_lsmix.py │ │ └── compute_fbank_musan.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── surt.png ├── libriheavy │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── compute_fbank_libriheavy.py │ │ ├── compute_fbank_musan.py │ │ ├── norm_text.py │ │ ├── prepare_manifest.py │ │ └── train_bpe_model.py │ │ ├── prepare.sh │ │ ├── prepare_prompt_asr.sh │ │ ├── shared │ │ ├── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── jit_pretrained.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── onnx_decode.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_coverter.py │ │ ├── subsampling.py │ │ ├── text_normalization.py │ │ ├── train.py │ │ └── zipformer.py │ │ └── zipformer_prompt_asr │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── dataset.py │ │ ├── decode_baseline.py │ │ ├── decode_bert.py │ │ ├── decode_bert_with_style_save_decoding_mp.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export_PromptASR.py │ │ ├── joiner.py │ │ ├── ls_text_normalization.py │ │ ├── model_baseline.py │ │ ├── model_with_BERT.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── subsampling.py │ │ ├── test_model.py │ │ ├── text_normalization.py │ │ ├── train_baseline.py │ │ ├── train_bert_encoder.py │ │ ├── transcribe_bert.py │ │ ├── utils.py │ │ └── zipformer.py ├── librilight │ └── SSL │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── dataset.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── finetune.py │ │ ├── hubert_ce.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrain.py │ │ ├── scaling.py │ │ ├── ssl_datamodule.py │ │ ├── utils.py │ │ ├── wav2vec2_module.py │ │ └── zipformer.py ├── librispeech │ ├── ASR │ │ ├── .gitignore │ │ ├── README.md │ │ ├── RESULTS-100hours.md │ │ ├── RESULTS.md │ │ ├── add_alignments.sh │ │ ├── conformer_ctc │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── ali.py │ │ │ ├── asr_datamodule.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── export.py │ │ │ ├── jit_pretrained_decode_with_H.py │ │ │ ├── jit_pretrained_decode_with_HL.py │ │ │ ├── jit_pretrained_decode_with_HLG.py │ │ │ ├── label_smoothing.py │ │ │ ├── pretrained.py │ │ │ ├── subsampling.py │ │ │ ├── test_label_smoothing.py │ │ │ ├── test_subsampling.py │ │ │ ├── test_transformer.py │ │ │ ├── train.py │ │ │ └── transformer.py │ │ ├── conformer_ctc2 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── attention.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── export.py │ │ │ ├── label_smoothing.py │ │ │ ├── optim.py │ │ │ ├── scaling.py │ │ │ ├── subsampling.py │ │ │ ├── train.py │ │ │ └── transformer.py │ │ ├── conformer_ctc3 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── jit_pretrained.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── test_model.py │ │ │ └── train.py │ │ ├── conformer_mmi │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── subsampling.py │ │ │ ├── test_subsampling.py │ │ │ ├── test_transformer.py │ │ │ ├── train-with-attention.py │ │ │ ├── train.py │ │ │ └── transformer.py │ │ ├── conv_emformer_transducer_stateless │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── emformer.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── scaling.py │ │ │ ├── stream.py │ │ │ ├── streaming_decode.py │ │ │ ├── test_emformer.py │ │ │ └── train.py │ │ ├── conv_emformer_transducer_stateless2 │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── do_not_use_it_directly.py │ │ │ ├── emformer.py │ │ │ ├── emformer2.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-for-ncnn.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── jit_pretrained.py │ │ │ ├── joiner.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── stream.py │ │ │ ├── streaming-ncnn-decode.py │ │ │ ├── streaming_decode.py │ │ │ ├── test_emformer.py │ │ │ └── train.py │ │ ├── distillation_with_hubert.sh │ │ ├── finetune.sh │ │ ├── local │ │ │ ├── __init__.py │ │ │ ├── add_alignment_librispeech.py │ │ │ ├── compile_hlg.py │ │ │ ├── compile_hlg_using_openfst.py │ │ │ ├── compile_lg.py │ │ │ ├── compute_fbank_gigaspeech_dev_test.py │ │ │ ├── compute_fbank_gigaspeech_splits.py │ │ │ ├── compute_fbank_librispeech.py │ │ │ ├── compute_fbank_musan.py │ │ │ ├── convert_transcript_words_to_tokens.py │ │ │ ├── display_manifest_statistics.py │ │ │ ├── download_lm.py │ │ │ ├── filter_cuts.py │ │ │ ├── generate_unique_lexicon.py │ │ │ ├── prepare_lang.py │ │ │ ├── prepare_lang_bpe.py │ │ │ ├── prepare_lang_fst.py │ │ │ ├── prepare_lm_training_data.py │ │ │ ├── preprocess_gigaspeech.py │ │ │ ├── sort_lm_training_data.py │ │ │ ├── test_load_XL_split.py │ │ │ ├── test_prepare_lang.py │ │ │ ├── train_bpe_model.py │ │ │ ├── validate_bpe_lexicon.py │ │ │ └── validate_manifest.py │ │ ├── long_file_recog.sh │ │ ├── long_file_recog │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── merge_chunks.py │ │ │ ├── recognize.py │ │ │ └── split_into_chunks.py │ │ ├── lstm_transducer_stateless │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── jit_pretrained.py │ │ │ ├── joiner.py │ │ │ ├── lstm.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── stream.py │ │ │ ├── streaming_decode.py │ │ │ ├── test_model.py │ │ │ ├── test_scaling_converter.py │ │ │ └── train.py │ │ ├── lstm_transducer_stateless2 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-for-ncnn.py │ │ │ ├── export-onnx-zh.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── gigaspeech.py │ │ │ ├── jit_pretrained.py │ │ │ ├── joiner.py │ │ │ ├── librispeech.py │ │ │ ├── lstm.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── ncnn-decode.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming-ncnn-decode.py │ │ │ ├── streaming-onnx-decode.py │ │ │ ├── test_lstmp.py │ │ │ └── train.py │ │ ├── lstm_transducer_stateless3 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-for-ncnn.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── jit_pretrained.py │ │ │ ├── joiner.py │ │ │ ├── lstm.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── stream.py │ │ │ ├── streaming_decode.py │ │ │ ├── test_model.py │ │ │ ├── test_scaling_converter.py │ │ │ └── train.py │ │ ├── prepare.sh │ │ ├── prepare_lm.sh │ │ ├── prepare_mmi.sh │ │ ├── pruned2_knowledge │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── decoder2.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── sampling.py │ │ │ ├── scaling.py │ │ │ ├── scaling_tmp.py │ │ │ └── train.py │ │ ├── pruned_stateless_emformer_rnnt2 │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── emformer.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── noam.py │ │ │ ├── subsampling.py │ │ │ ├── test_emformer.py │ │ │ ├── test_model.py │ │ │ └── train.py │ │ ├── pruned_transducer_stateless │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── my_profile.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_decode.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── pretrained.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── subsampling.py │ │ │ ├── test_decoder.py │ │ │ ├── test_model.py │ │ │ ├── train.py │ │ │ └── transformer.py │ │ ├── pruned_transducer_stateless2 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── test_model.py │ │ │ └── train.py │ │ ├── pruned_transducer_stateless3 │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode-giga.py │ │ │ ├── decode.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── gigaspeech.py │ │ │ ├── gigaspeech_scoring.py │ │ │ ├── jit_pretrained.py │ │ │ ├── joiner.py │ │ │ ├── librispeech.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_decode.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── test_model.py │ │ │ ├── test_onnx.py │ │ │ ├── test_scaling.py │ │ │ ├── test_scaling_converter.py │ │ │ └── train.py │ │ ├── pruned_transducer_stateless4 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── my_profile.py │ │ │ ├── optim.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── test_model.py │ │ │ └── train.py │ │ ├── pruned_transducer_stateless5 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx-streaming.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_decode.py │ │ │ ├── onnx_pretrained-streaming.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── test_model.py │ │ │ └── train.py │ │ ├── pruned_transducer_stateless6 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── extract_codebook_index.py │ │ │ ├── hubert_decode.py │ │ │ ├── hubert_xlarge.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── scaling.py │ │ │ ├── test_model.py │ │ │ ├── train.py │ │ │ └── vq_utils.py │ │ ├── pruned_transducer_stateless7 │ │ │ ├── __init__.py │ │ │ ├── alignment.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── compute_ali.py │ │ │ ├── decode.py │ │ │ ├── decode_gigaspeech.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── finetune.py │ │ │ ├── generate_model_from_checkpoint.py │ │ │ ├── gigaspeech.py │ │ │ ├── gigaspeech_scoring.py │ │ │ ├── jit_pretrained.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── my_profile.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_decode.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── test_compute_ali.py │ │ │ ├── test_model.py │ │ │ ├── test_onnx.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ │ ├── pruned_transducer_stateless7_ctc │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── ctc_decode.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── jit_pretrained.py │ │ │ ├── jit_pretrained_ctc.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── pretrained_ctc.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── test_model.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ │ ├── pruned_transducer_stateless7_ctc_bs │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── ctc_decode.py │ │ │ ├── ctc_guide_decode_bs.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── export_onnx.py │ │ │ ├── frame_reducer.py │ │ │ ├── jit_pretrained.py │ │ │ ├── jit_pretrained_ctc.py │ │ │ ├── joiner.py │ │ │ ├── lconv.py │ │ │ ├── model.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── onnx_wrapper.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── pretrained_ctc.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── test_model.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ │ ├── pruned_transducer_stateless7_streaming │ │ │ ├── README.md │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── do_not_use_it_directly.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-for-ncnn-zh.py │ │ │ ├── export-for-ncnn.py │ │ │ ├── export-onnx-zh.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── export_rknn.py │ │ │ ├── jit_pretrained.py │ │ │ ├── jit_trace_export.py │ │ │ ├── jit_trace_pretrained.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── ncnn_custom_layer.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_model_wrapper.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming-ncnn-decode.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── test_model.py │ │ │ ├── test_rknn_on_cpu_simulator.py │ │ │ ├── train.py │ │ │ ├── zipformer.py │ │ │ └── zipformer_for_ncnn_export_only.py │ │ ├── pruned_transducer_stateless7_streaming_multi │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decode_gigaspeech.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── do_not_use_it_directly.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-for-ncnn-zh.py │ │ │ ├── export-for-ncnn.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── gigaspeech.py │ │ │ ├── gigaspeech_asrmodule.py │ │ │ ├── gigaspeech_scoring.py │ │ │ ├── jit_pretrained.py │ │ │ ├── jit_trace_export.py │ │ │ ├── jit_trace_pretrained.py │ │ │ ├── joiner.py │ │ │ ├── librispeech.py │ │ │ ├── model.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_model_wrapper.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming-ncnn-decode.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── test_model.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ │ ├── pruned_transducer_stateless8 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── gigaspeech.py │ │ │ ├── jit_pretrained.py │ │ │ ├── joiner.py │ │ │ ├── librispeech.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ │ ├── shared │ │ ├── streaming_conformer_ctc │ │ │ ├── README.md │ │ │ ├── asr_datamodule.py │ │ │ ├── conformer.py │ │ │ ├── label_smoothing.py │ │ │ ├── streaming_decode.py │ │ │ ├── subsampling.py │ │ │ ├── train.py │ │ │ └── transformer.py │ │ ├── tdnn_lstm_ctc │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── decode.py │ │ │ ├── model.py │ │ │ ├── pretrained.py │ │ │ └── train.py │ │ ├── tiny_transducer_ctc │ │ │ ├── README.md │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── ctc_decode.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── jit_pretrained.py │ │ │ ├── jit_pretrained_ctc.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── pretrained.py │ │ │ ├── pretrained_ctc.py │ │ │ ├── scaling.py │ │ │ └── train.py │ │ ├── transducer │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── pretrained.py │ │ │ ├── rnn.py │ │ │ ├── subsampling.py │ │ │ ├── test_conformer.py │ │ │ ├── test_decoder.py │ │ │ ├── test_joiner.py │ │ │ ├── test_rnn.py │ │ │ ├── test_transducer.py │ │ │ ├── test_transformer.py │ │ │ ├── train.py │ │ │ └── transformer.py │ │ ├── transducer_lstm │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── noam.py │ │ │ ├── subsampling.py │ │ │ ├── test_encoder.py │ │ │ └── train.py │ │ ├── transducer_stateless │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── alignment.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── compute_ali.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── pretrained.py │ │ │ ├── subsampling.py │ │ │ ├── test_compute_ali.py │ │ │ ├── test_conformer.py │ │ │ ├── test_decoder.py │ │ │ ├── test_joiner.py │ │ │ ├── test_model.py │ │ │ ├── train.py │ │ │ └── transformer.py │ │ ├── transducer_stateless2 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── pretrained.py │ │ │ ├── subsampling.py │ │ │ ├── test_model.py │ │ │ ├── train.py │ │ │ └── transformer.py │ │ ├── transducer_stateless_multi_datasets │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── gigaspeech.py │ │ │ ├── joiner.py │ │ │ ├── librispeech.py │ │ │ ├── model.py │ │ │ ├── pretrained.py │ │ │ ├── subsampling.py │ │ │ ├── test_asr_datamodule.py │ │ │ ├── test_decoder.py │ │ │ ├── train.py │ │ │ └── transformer.py │ │ ├── zipformer │ │ │ ├── .gitignore │ │ │ ├── asr_datamodule.py │ │ │ ├── attention_decoder.py │ │ │ ├── beam_search.py │ │ │ ├── ctc_decode.py │ │ │ ├── decode.py │ │ │ ├── decode_gigaspeech.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx-ctc.py │ │ │ ├── export-onnx-streaming-ctc.py │ │ │ ├── export-onnx-streaming.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── finetune.py │ │ │ ├── generate_averaged_model.py │ │ │ ├── jit_pretrained.py │ │ │ ├── jit_pretrained_ctc.py │ │ │ ├── jit_pretrained_streaming.py │ │ │ ├── joiner.py │ │ │ ├── label_smoothing.py │ │ │ ├── model.py │ │ │ ├── my_profile.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_decode.py │ │ │ ├── onnx_pretrained-streaming-ctc.py │ │ │ ├── onnx_pretrained-streaming.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── onnx_pretrained_ctc.py │ │ │ ├── onnx_pretrained_ctc_H.py │ │ │ ├── onnx_pretrained_ctc_HL.py │ │ │ ├── onnx_pretrained_ctc_HLG.py │ │ │ ├── onnx_pretrained_ctc_HLG_streaming.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── pretrained_ctc.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── subsampling.py │ │ │ ├── test_scaling.py │ │ │ ├── test_subsampling.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ │ ├── zipformer_adapter │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decode_gigaspeech.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── onnx_decode.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── subsampling.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ │ ├── zipformer_ctc │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── label_smoothing.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── subsampling.py │ │ │ ├── train.py │ │ │ ├── transformer.py │ │ │ └── zipformer.py │ │ ├── zipformer_lora │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode_gigaspeech.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── finetune.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── subsampling.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ │ └── zipformer_mmi │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── decode.py │ │ │ ├── encoder_interface.py │ │ │ ├── export.py │ │ │ ├── jit_pretrained.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── test_model.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ ├── SSL │ │ ├── hubert │ │ │ ├── asr_datamodule.py │ │ │ ├── attention_module.py │ │ │ ├── beam_search.py │ │ │ ├── dataset.py │ │ │ ├── decode.py │ │ │ ├── decode_ce.py │ │ │ ├── decoder.py │ │ │ ├── finetune.py │ │ │ ├── finetune_ce.py │ │ │ ├── hubert.py │ │ │ ├── hubert_ce.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── pretrain.py │ │ │ ├── pretrain_ce.py │ │ │ ├── scaling.py │ │ │ ├── ssl_datamodule.py │ │ │ ├── utils.py │ │ │ └── wav2vec2_module.py │ │ ├── local │ │ │ ├── attach_kmeans_to_supervisions.py │ │ │ ├── convert_checkpoint_from_fairseq.py │ │ │ ├── prepare_char.py │ │ │ ├── prepare_lang.py │ │ │ ├── process_librispeech4finetune.py │ │ │ ├── process_librispeech4pretrain.py │ │ │ └── process_raw_cuts.py │ │ ├── shared │ │ └── zipformer │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── dataset.py │ │ │ ├── decode.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── finetune.py │ │ │ ├── hubert_ce.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── optim.py │ │ │ ├── pretrain.py │ │ │ ├── scaling.py │ │ │ ├── ssl_datamodule.py │ │ │ ├── utils.py │ │ │ ├── wav2vec2_module.py │ │ │ └── zipformer.py │ └── WSASR │ │ ├── README.md │ │ ├── conformer_ctc2 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── attention.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decode_phone.py │ │ ├── export.py │ │ ├── label_smoothing.py │ │ ├── optim.py │ │ ├── scaling.py │ │ ├── subsampling.py │ │ ├── train.py │ │ ├── train_phone.py │ │ └── transformer.py │ │ ├── figures │ │ ├── del.png │ │ ├── ins.png │ │ ├── otc_emission.drawio.png │ │ ├── otc_g.png │ │ ├── otc_training_graph.drawio.png │ │ └── sub.png │ │ ├── local │ │ ├── compile_hlg.py │ │ ├── compute_fbank_librispeech.py │ │ ├── compute_ssl_librispeech.py │ │ ├── download_lm.py │ │ ├── filter_cuts.py │ │ ├── get_words_from_lexicon.py │ │ ├── make_error_cutset.py │ │ ├── prepare_lang.py │ │ ├── prepare_otc_lang.py │ │ ├── prepare_otc_lang_bpe.py │ │ ├── train_bpe_model.py │ │ ├── validate_bpe_lexicon.py │ │ └── validate_manifest.py │ │ ├── prepare.sh │ │ └── shared ├── libritts │ ├── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ │ ├── compile_hlg.py │ │ │ ├── compile_lg.py │ │ │ ├── compute_fbank_libritts.py │ │ │ ├── compute_fbank_musan.py │ │ │ ├── convert_transcript_words_to_tokens.py │ │ │ ├── display_manifest_statistics.py │ │ │ ├── download_lm.py │ │ │ ├── norm_text.py │ │ │ ├── prepare_lang.py │ │ │ ├── prepare_lang_bpe.py │ │ │ ├── prepare_lang_fst.py │ │ │ ├── prepare_lm_training_data.py │ │ │ ├── train_bpe_model.py │ │ │ ├── validate_bpe_lexicon.py │ │ │ └── validate_manifest.py │ │ ├── prepare.sh │ │ ├── prepare_lm.sh │ │ ├── shared │ │ └── zipformer │ │ │ ├── .gitignore │ │ │ ├── asr_datamodule.py │ │ │ ├── attention_decoder.py │ │ │ ├── beam_search.py │ │ │ ├── ctc_decode.py │ │ │ ├── decode.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx-ctc.py │ │ │ ├── export-onnx-streaming-ctc.py │ │ │ ├── export-onnx-streaming.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── generate_averaged_model.py │ │ │ ├── jit_pretrained.py │ │ │ ├── jit_pretrained_ctc.py │ │ │ ├── jit_pretrained_streaming.py │ │ │ ├── joiner.py │ │ │ ├── label_smoothing.py │ │ │ ├── model.py │ │ │ ├── my_profile.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_decode.py │ │ │ ├── onnx_pretrained-streaming-ctc.py │ │ │ ├── onnx_pretrained-streaming.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── onnx_pretrained_ctc.py │ │ │ ├── onnx_pretrained_ctc_H.py │ │ │ ├── onnx_pretrained_ctc_HL.py │ │ │ ├── onnx_pretrained_ctc_HLG.py │ │ │ ├── onnx_pretrained_ctc_HLG_streaming.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── pretrained_ctc.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── subsampling.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ ├── CODEC │ │ ├── encodec │ │ │ ├── base_discriminators.py │ │ │ ├── binary.py │ │ │ ├── codec_datamodule.py │ │ │ ├── discriminators.py │ │ │ ├── encodec.py │ │ │ ├── infer.py │ │ │ ├── loss.py │ │ │ ├── modules │ │ │ │ ├── __init__.py │ │ │ │ ├── conv.py │ │ │ │ ├── lstm.py │ │ │ │ ├── norm.py │ │ │ │ ├── seanet.py │ │ │ │ └── transformer.py │ │ │ ├── quantization │ │ │ │ ├── __init__.py │ │ │ │ ├── ac.py │ │ │ │ ├── core_vq.py │ │ │ │ ├── distrib.py │ │ │ │ └── vq.py │ │ │ ├── scheduler.py │ │ │ ├── train.py │ │ │ └── utils.py │ │ ├── local │ │ │ ├── compute_spectrogram_libritts.py │ │ │ ├── display_manifest_statistics.py │ │ │ └── validate_manifest.py │ │ ├── prepare.sh │ │ └── shared │ └── TTS │ │ ├── README.md │ │ ├── local │ │ ├── compute_neural_codec_and_prepare_text_tokens.py │ │ ├── compute_spectrogram_libritts.py │ │ ├── prepare_token_file.py │ │ ├── prepare_tokens_libritts.py │ │ └── validate_manifest.py │ │ ├── prepare.sh │ │ ├── shared │ │ ├── valle │ │ └── vits │ │ ├── duration_predictor.py │ │ ├── flow.py │ │ ├── generator.py │ │ ├── hifigan.py │ │ ├── infer.py │ │ ├── loss.py │ │ ├── monotonic_align │ │ ├── posterior_encoder.py │ │ ├── residual_coupling.py │ │ ├── test_onnx.py │ │ ├── text_encoder.py │ │ ├── tokenizer.py │ │ ├── train.py │ │ ├── transform.py │ │ ├── tts_datamodule.py │ │ ├── utils.py │ │ ├── vits.py │ │ └── wavenet.py ├── ljspeech │ └── TTS │ │ ├── .gitignore │ │ ├── README.md │ │ ├── local │ │ ├── audio.py │ │ ├── compute_fbank_ljspeech.py │ │ ├── compute_fbank_statistics.py │ │ ├── compute_spectrogram_ljspeech.py │ │ ├── display_manifest_statistics.py │ │ ├── fbank.py │ │ ├── prepare_token_file.py │ │ ├── prepare_tokens_ljspeech.py │ │ └── validate_manifest.py │ │ ├── matcha │ │ ├── LICENSE │ │ ├── __init__.py │ │ ├── audio.py │ │ ├── export_onnx.py │ │ ├── export_onnx_hifigan.py │ │ ├── fbank.py │ │ ├── hifigan │ │ │ ├── LICENSE │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── config.py │ │ │ ├── denoiser.py │ │ │ ├── env.py │ │ │ ├── meldataset.py │ │ │ ├── models.py │ │ │ └── xutils.py │ │ ├── infer.py │ │ ├── model.py │ │ ├── models │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── components │ │ │ │ ├── __init__.py │ │ │ │ ├── decoder.py │ │ │ │ ├── flow_matching.py │ │ │ │ ├── text_encoder.py │ │ │ │ └── transformer.py │ │ │ └── matcha_tts.py │ │ ├── monotonic_align │ │ │ ├── .gitignore │ │ │ ├── __init__.py │ │ │ ├── core.pyx │ │ │ └── setup.py │ │ ├── onnx_pretrained.py │ │ ├── requirements.txt │ │ ├── tokenizer.py │ │ ├── train.py │ │ ├── tts_datamodule.py │ │ └── utils.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── vits │ │ ├── README.md │ │ ├── duration_predictor.py │ │ ├── export-onnx.py │ │ ├── flow.py │ │ ├── generator.py │ │ ├── hifigan.py │ │ ├── infer.py │ │ ├── loss.py │ │ ├── monotonic_align │ │ ├── .gitignore │ │ ├── __init__.py │ │ ├── core.pyx │ │ └── setup.py │ │ ├── posterior_encoder.py │ │ ├── residual_coupling.py │ │ ├── test_model.py │ │ ├── test_onnx.py │ │ ├── text_encoder.py │ │ ├── tokenizer.py │ │ ├── train.py │ │ ├── transform.py │ │ ├── tts_datamodule.py │ │ ├── utils.py │ │ ├── vits.py │ │ └── wavenet.py ├── mdcc │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── compile_hlg.py │ │ ├── compile_hlg_using_openfst.py │ │ ├── compile_lg.py │ │ ├── compute_fbank_mdcc.py │ │ ├── display_manifest_statistics.py │ │ ├── prepare_char.py │ │ ├── prepare_char_lm_training_data.py │ │ ├── prepare_lang.py │ │ ├── prepare_lang_fst.py │ │ ├── preprocess_mdcc.py │ │ ├── text2segments.py │ │ └── text2token.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── zipformer │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx-ctc.py │ │ ├── export-onnx-streaming-ctc.py │ │ ├── export-onnx-streaming.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── onnx_check.py │ │ ├── onnx_decode.py │ │ ├── optim.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── zipformer.py ├── mgb2 │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── conformer_ctc │ │ ├── __init__.py │ │ ├── ali.py │ │ ├── asr_datamodule.py │ │ ├── compile_hlg.py │ │ ├── compute_fbank_musan.py │ │ ├── conformer.py │ │ ├── convert_transcript_words_to_tokens.py │ │ ├── decode.py │ │ ├── download_lm.py │ │ ├── export.py │ │ ├── generate_unique_lexicon.py │ │ ├── label_smoothing.py │ │ ├── pretrained.py │ │ ├── subsampling.py │ │ ├── test_label_smoothing.py │ │ ├── test_subsampling.py │ │ ├── test_transformer.py │ │ ├── train.py │ │ └── transformer.py │ │ ├── local │ │ ├── __init__.py │ │ ├── compile_hlg.py │ │ ├── compute_fbank_mgb2.py │ │ ├── compute_fbank_musan.py │ │ ├── convert_transcript_words_to_tokens.py │ │ ├── display_manifest_statistics.py │ │ ├── generate_unique_lexicon.py │ │ ├── prep_mgb2_lexicon.sh │ │ ├── prepare_lang.py │ │ ├── prepare_lang_bpe.py │ │ ├── prepare_mgb2_lexicon.py │ │ └── test_prepare_lang.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless5 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── test_model.py │ │ └── train.py │ │ └── shared ├── multi_ja_en │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── compute_fbank_reazonspeech.py │ │ ├── display_manifest_statistics.py │ │ ├── prepare_char.py │ │ ├── prepare_for_bpe_model.py │ │ ├── prepare_lang.py │ │ ├── prepare_lang_bbpe.py │ │ ├── prepare_lang_char.py │ │ ├── prepare_words.py │ │ ├── text2segments.py │ │ ├── text2token.py │ │ ├── train_bbpe_model.py │ │ ├── utils │ │ │ ├── asr_datamodule.py │ │ │ └── tokenizer.py │ │ ├── validate_bpe_lexicon.py │ │ └── validate_manifest.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── ctc_decode.py │ │ ├── decode.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── do_not_use_it_directly.py │ │ ├── encoder_interface.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── generate_averaged_model.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── multi_dataset.py │ │ ├── my_profile.py │ │ ├── onnx_decode.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── subsampling.py │ │ ├── test_scaling.py │ │ ├── test_subsampling.py │ │ ├── tokenizer.py │ │ ├── train.py │ │ └── zipformer.py ├── multi_zh-hans │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── bpe_model_to_tokens.py │ │ ├── compile_lg.py │ │ ├── compute_fbank_kespeech_dev_test.py │ │ ├── compute_fbank_kespeech_splits.py │ │ ├── compute_fbank_magicdata.py │ │ ├── compute_fbank_primewords.py │ │ ├── compute_fbank_stcmds.py │ │ ├── compute_fbank_thchs30.py │ │ ├── prepare_char.py │ │ ├── prepare_for_bpe_model.py │ │ ├── prepare_lang.py │ │ ├── prepare_lang_bpe.py │ │ ├── preprocess_kespeech.py │ │ ├── text2token.py │ │ ├── train_bpe_model.py │ │ └── validate_bpe_lexicon.py │ │ ├── prepare.sh │ │ ├── shared │ │ ├── whisper │ │ ├── asr_datamodule.py │ │ ├── decode.py │ │ ├── ds_config_zero1.json │ │ ├── label_smoothing.py │ │ ├── multi_dataset.py │ │ ├── optim.py │ │ ├── requirements.txt │ │ ├── train.py │ │ ├── whisper_decoder_forward_monkey_patch.py │ │ └── whisper_encoder_forward_monkey_patch.py │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── ctc_decode.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx-streaming-ctc.py │ │ ├── export-onnx-streaming.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── generate_averaged_model.py │ │ ├── jit_pretrained.py │ │ ├── jit_pretrained_ctc.py │ │ ├── jit_pretrained_streaming.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── multi_dataset.py │ │ ├── onnx_check.py │ │ ├── onnx_decode.py │ │ ├── onnx_pretrained-streaming-ctc.py │ │ ├── onnx_pretrained-streaming.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── zipformer.py ├── multi_zh_en │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── compile_lg.py │ │ ├── prepare_char.py │ │ ├── prepare_for_bpe_model.py │ │ ├── prepare_lang.py │ │ ├── prepare_lang_bbpe.py │ │ ├── prepare_lang_bpe.py │ │ ├── prepare_words.py │ │ ├── text2segments.py │ │ ├── text2token.py │ │ ├── train_bbpe_model.py │ │ └── validate_bpe_lexicon.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx-streaming.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── generate_averaged_model.py │ │ ├── jit_pretrained.py │ │ ├── jit_pretrained_ctc.py │ │ ├── jit_pretrained_streaming.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── multi_dataset.py │ │ ├── onnx_check.py │ │ ├── onnx_decode.py │ │ ├── onnx_pretrained-streaming.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── zipformer.py ├── must_c │ └── ST │ │ ├── local │ │ ├── compute_fbank_musan.py │ │ ├── compute_fbank_must_c.py │ │ ├── get_text.py │ │ ├── get_words.py │ │ ├── normalize_punctuation.py │ │ ├── prepare_lang.py │ │ ├── prepare_lang_bpe.py │ │ ├── preprocess_must_c.py │ │ ├── remove_non_native_characters.py │ │ ├── remove_punctuation.py │ │ ├── test_normalize_punctuation.py │ │ ├── test_remove_non_native_characters.py │ │ ├── test_remove_punctuation.py │ │ ├── train_bpe_model.py │ │ └── validate_bpe_lexicon.py │ │ ├── prepare.sh │ │ └── shared ├── ptb │ └── LM │ │ ├── README.md │ │ ├── local │ │ ├── prepare_lm_training_data.py │ │ ├── sort_lm_training_data.py │ │ ├── test_prepare_lm_training_data.py │ │ └── train_bpe_model.py │ │ ├── prepare.sh │ │ ├── rnn_lm │ │ ├── shared │ │ └── train-rnn-lm.sh ├── reazonspeech │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── compute_fbank_reazonspeech.py │ │ ├── display_manifest_statistics.py │ │ ├── prepare_lang_char.py │ │ ├── utils │ │ │ ├── asr_datamodule.py │ │ │ └── tokenizer.py │ │ └── validate_manifest.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── ctc_decode.py │ │ ├── decode.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── do_not_use_it_directly.py │ │ ├── encoder_interface.py │ │ ├── export-onnx.py │ │ ├── export.py │ │ ├── generate_averaged_model.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── my_profile.py │ │ ├── onnx_pretrained.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── subsampling.py │ │ ├── test_scaling.py │ │ ├── test_subsampling.py │ │ ├── tokenizer.py │ │ ├── train.py │ │ └── zipformer.py ├── speech_llm │ └── ASR_LLM │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── assets │ │ └── framework.png │ │ ├── prepare.sh │ │ ├── shared │ │ └── whisper_llm_zh │ │ ├── asr_datamodule.py │ │ ├── decode.py │ │ ├── ds_config_zero1.json │ │ ├── label_smoothing.py │ │ ├── model.py │ │ ├── multi_dataset.py │ │ ├── requirements.txt │ │ ├── train.py │ │ └── whisper_encoder_forward_monkey_patch.py ├── speechio │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── compute_fbank_speechio.py │ │ ├── display_manifest_statistics.py │ │ ├── normalize_results.py │ │ └── speechio_norm.py │ │ ├── prepare.sh │ │ ├── shared │ │ ├── whisper │ │ ├── asr_datamodule.py │ │ ├── decode.py │ │ ├── multi_dataset.py │ │ ├── requirements.txt │ │ ├── whisper_decoder_forward_monkey_patch.py │ │ └── whisper_encoder_forward_monkey_patch.py │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── ctc_decode.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── multi_dataset.py │ │ ├── optim.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── zipformer.py ├── spgispeech │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── __init__.py │ │ ├── compile_hlg.py │ │ ├── compute_fbank_musan.py │ │ ├── compute_fbank_spgispeech.py │ │ ├── prepare_lang.py │ │ ├── prepare_lang_bpe.py │ │ ├── prepare_splits.py │ │ └── train_bpe_model.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless2 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── scaling.py │ │ └── train.py │ │ ├── shared │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── zipformer.py ├── swbd │ └── ASR │ │ ├── .gitignore │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── conformer_ctc │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── export.py │ │ ├── label_smoothing.py │ │ ├── pretrained.py │ │ ├── sclite_scoring.py │ │ ├── subsampling.py │ │ ├── test_label_smoothing.py │ │ ├── test_subsampling.py │ │ ├── test_transformer.py │ │ ├── train.py │ │ └── transformer.py │ │ ├── local │ │ ├── compile_hlg.py │ │ ├── compile_lg.py │ │ ├── compute_fbank_eval2000.py │ │ ├── compute_fbank_swbd.py │ │ ├── convert_transcript_words_to_tokens.py │ │ ├── dict.patch │ │ ├── display_manifest_statistics.py │ │ ├── extend_segments.pl │ │ ├── filter_cuts.py │ │ ├── filter_empty_text.py │ │ ├── format_acronyms_dict.py │ │ ├── generate_unique_lexicon.py │ │ ├── map_acronyms_transcripts.py │ │ ├── normalize_and_filter_supervisions.py │ │ ├── normalize_eval2000.py │ │ ├── prepare_lang.py │ │ ├── prepare_lang_bpe.py │ │ ├── prepare_lm_training_data.py │ │ ├── rt03_data_prep.sh │ │ ├── sort_lm_training_data.py │ │ ├── swbd1_data_prep.sh │ │ ├── swbd1_map_words.pl │ │ ├── swbd1_prepare_dict.sh │ │ ├── train_bpe_model.py │ │ └── validate_bpe_lexicon.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── utils │ │ ├── filter_scp.pl │ │ ├── fix_data_dir.sh │ │ ├── parse_options.sh │ │ ├── spk2utt_to_utt2spk.pl │ │ └── utt2spk_to_spk2utt.pl ├── tal_csasr │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── __init__.py │ │ ├── compute_fbank_musan.py │ │ ├── compute_fbank_tal_csasr.py │ │ ├── display_manifest_statistics.py │ │ ├── prepare_char.py │ │ ├── prepare_lang.py │ │ ├── prepare_words.py │ │ ├── test_prepare_lang.py │ │ ├── text2segments.py │ │ ├── text2token.py │ │ ├── text_normalize.py │ │ ├── tokenize_with_bpe_model.py │ │ └── train_bbpe_model.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless5 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── lstmp.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── test_model.py │ │ └── train.py │ │ ├── pruned_transducer_stateless7_bbpe │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── jit_pretrained.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── test_model.py │ │ ├── train.py │ │ └── zipformer.py │ │ └── shared ├── tedlium3 │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── conformer_ctc2 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── attention.py │ │ ├── combiner.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── export.py │ │ ├── label_smoothing.py │ │ ├── local │ │ ├── lstmp.py │ │ ├── optim.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── transformer.py │ │ ├── local │ │ ├── __init__.py │ │ ├── compile_hlg.py │ │ ├── compute_fbank_musan.py │ │ ├── compute_fbank_tedlium.py │ │ ├── convert_transcript_words_to_bpe_ids.py │ │ ├── display_manifest_statistics.py │ │ ├── prepare_lang_bpe.py │ │ ├── prepare_transcripts.py │ │ ├── prepare_words.py │ │ └── train_bpe_model.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── local │ │ ├── model.py │ │ ├── pretrained.py │ │ ├── subsampling.py │ │ ├── test_decoder.py │ │ ├── train.py │ │ └── transformer.py │ │ ├── shared │ │ ├── transducer_stateless │ │ ├── README.md │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── local │ │ ├── model.py │ │ ├── pretrained.py │ │ ├── subsampling.py │ │ ├── test_decoder.py │ │ ├── train.py │ │ └── transformer.py │ │ └── zipformer │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── local │ │ ├── model.py │ │ ├── my_profile.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── zipformer.py ├── timit │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── __init__.py │ │ ├── compile_hlg.py │ │ ├── compute_fbank_musan.py │ │ ├── compute_fbank_timit.py │ │ ├── prepare_lang.py │ │ └── prepare_lexicon.py │ │ ├── prepare.sh │ │ ├── shared │ │ ├── tdnn_ligru_ctc │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── decode.py │ │ ├── model.py │ │ ├── pretrained.py │ │ └── train.py │ │ └── tdnn_lstm_ctc │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── decode.py │ │ ├── model.py │ │ ├── pretrained.py │ │ └── train.py ├── vctk │ └── TTS │ │ ├── README.md │ │ ├── local │ │ ├── compute_spectrogram_vctk.py │ │ ├── display_manifest_statistics.py │ │ ├── prepare_token_file.py │ │ ├── prepare_tokens_vctk.py │ │ └── validate_manifest.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── vits │ │ ├── duration_predictor.py │ │ ├── export-onnx.py │ │ ├── flow.py │ │ ├── generator.py │ │ ├── hifigan.py │ │ ├── infer.py │ │ ├── loss.py │ │ ├── monotonic_align │ │ ├── posterior_encoder.py │ │ ├── residual_coupling.py │ │ ├── test_onnx.py │ │ ├── text_encoder.py │ │ ├── tokenizer.py │ │ ├── train.py │ │ ├── transform.py │ │ ├── tts_datamodule.py │ │ ├── utils.py │ │ ├── vits.py │ │ └── wavenet.py ├── voxpopuli │ └── ASR │ │ ├── README.md │ │ ├── local │ │ ├── compute_fbank.py │ │ ├── compute_fbank_musan.py │ │ ├── display_manifest_statistics.py │ │ ├── duration_from_supervision_manifest.py │ │ ├── filter_cuts.py │ │ ├── prepare_lang_bpe.py │ │ ├── preprocess_voxpopuli.py │ │ ├── separate_punctuation.py │ │ ├── text_from_manifest.py │ │ ├── train_bpe_model.py │ │ ├── uppercase_begin_of_sentence.py │ │ ├── validate_bpe_lexicon.py │ │ └── validate_cutset_manifest.py │ │ ├── prepare.sh │ │ └── shared ├── wenetspeech │ ├── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── finetune.sh │ │ ├── local │ │ │ ├── compile_lg.py │ │ │ ├── compute_fbank_musan.py │ │ │ ├── compute_fbank_wenetspeech_dev_test.py │ │ │ ├── compute_fbank_wenetspeech_splits.py │ │ │ ├── display_manifest_statistics.py │ │ │ ├── fix_manifest.py │ │ │ ├── prepare_char.py │ │ │ ├── prepare_char_lm_training_data.py │ │ │ ├── prepare_dataset_from_kaldi_dir.py │ │ │ ├── prepare_lang.py │ │ │ ├── prepare_pinyin.py │ │ │ ├── prepare_words.py │ │ │ ├── preprocess_wenetspeech.py │ │ │ ├── sort_lm_training_data.py │ │ │ ├── text2segments.py │ │ │ └── text2token.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless2 │ │ │ ├── __init__.py │ │ │ ├── aishell.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decode_aishell.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── finetune.py │ │ │ ├── jit_pretrained.py │ │ │ ├── joiner.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ └── train.py │ │ ├── pruned_transducer_stateless5 │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── conformer.py │ │ │ ├── decode.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx-streaming.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── joiner.py │ │ │ ├── lstmp.py │ │ │ ├── model.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_pretrained-streaming.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ └── train.py │ │ ├── shared │ │ ├── whisper │ │ │ ├── asr_datamodule.py │ │ │ ├── decode.py │ │ │ ├── ds_config_zero1.json │ │ │ ├── label_smoothing.py │ │ │ ├── optim.py │ │ │ ├── requirements.txt │ │ │ ├── train.py │ │ │ └── whisper_encoder_forward_monkey_patch.py │ │ └── zipformer │ │ │ ├── __init__.py │ │ │ ├── asr_datamodule.py │ │ │ ├── beam_search.py │ │ │ ├── decode.py │ │ │ ├── decode_stream.py │ │ │ ├── decoder.py │ │ │ ├── encoder_interface.py │ │ │ ├── export-onnx-streaming.py │ │ │ ├── export-onnx.py │ │ │ ├── export.py │ │ │ ├── jit_pretrained.py │ │ │ ├── jit_pretrained_streaming.py │ │ │ ├── joiner.py │ │ │ ├── model.py │ │ │ ├── onnx_check.py │ │ │ ├── onnx_decode.py │ │ │ ├── onnx_pretrained-streaming.py │ │ │ ├── onnx_pretrained.py │ │ │ ├── optim.py │ │ │ ├── pretrained.py │ │ │ ├── scaling.py │ │ │ ├── scaling_converter.py │ │ │ ├── streaming_beam_search.py │ │ │ ├── streaming_decode.py │ │ │ ├── subsampling.py │ │ │ ├── train.py │ │ │ └── zipformer.py │ └── KWS │ │ ├── RESULTS.md │ │ ├── prepare.sh │ │ ├── run.sh │ │ ├── shared │ │ └── zipformer │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode-asr.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export-onnx-streaming.py │ │ ├── export.py │ │ ├── finetune.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── subsampling.py │ │ ├── train.py │ │ └── zipformer.py ├── wenetspeech4tts │ └── TTS │ │ ├── README.md │ │ ├── f5-tts │ │ ├── generate_averaged_model.py │ │ ├── infer.py │ │ ├── model │ │ │ ├── README.md │ │ │ ├── cfm.py │ │ │ ├── dit.py │ │ │ ├── modules.py │ │ │ └── utils.py │ │ ├── requirements.txt │ │ ├── speech_synthesis.py │ │ ├── train.py │ │ ├── tts_datamodule.py │ │ ├── utils.py │ │ └── vocab.txt │ │ ├── local │ │ ├── attach_speech_tokens.py │ │ ├── audio.py │ │ ├── compute_mel_feat.py │ │ ├── compute_neural_codec_and_prepare_text_tokens.py │ │ ├── compute_wer.sh │ │ ├── display_manifest_statistics.py │ │ ├── fbank.py │ │ └── offline-decode-files.py │ │ ├── prepare.sh │ │ ├── shared │ │ └── valle │ │ ├── compute_neural_codec_and_prepare_text_tokens.py │ │ ├── infer.py │ │ ├── optim.py │ │ ├── requirements.txt │ │ ├── tokenizer.py │ │ ├── train.py │ │ ├── tts_datamodule.py │ │ └── valle.py ├── xbmu_amdo31 │ └── ASR │ │ ├── README.md │ │ ├── RESULTS.md │ │ ├── local │ │ ├── compile_hlg.py │ │ ├── compile_lg.py │ │ ├── compute_fbank_musan.py │ │ ├── compute_fbank_xbmu_amdo31.py │ │ ├── convert_transcript_words_to_tokens.py │ │ ├── filter_cuts.py │ │ ├── generate_unique_lexicon.py │ │ ├── prepare_lang.py │ │ ├── prepare_lang_bpe.py │ │ ├── prepare_lm_training_data.py │ │ ├── sort_lm_training_data.py │ │ ├── train_bpe_model.py │ │ └── validate_bpe_lexicon.py │ │ ├── prepare.sh │ │ ├── pruned_transducer_stateless5 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── conformer.py │ │ ├── decode.py │ │ ├── decode_stream.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── joiner.py │ │ ├── lstmp.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── streaming_beam_search.py │ │ ├── streaming_decode.py │ │ ├── test_model.py │ │ └── train.py │ │ ├── pruned_transducer_stateless7 │ │ ├── __init__.py │ │ ├── asr_datamodule.py │ │ ├── beam_search.py │ │ ├── decode.py │ │ ├── decoder.py │ │ ├── encoder_interface.py │ │ ├── export.py │ │ ├── jit_pretrained.py │ │ ├── joiner.py │ │ ├── model.py │ │ ├── optim.py │ │ ├── pretrained.py │ │ ├── scaling.py │ │ ├── scaling_converter.py │ │ ├── test_model.py │ │ ├── train.py │ │ └── zipformer.py │ │ └── shared └── yesno │ └── ASR │ ├── README.md │ ├── local │ ├── compile_hlg.py │ ├── compute_fbank_yesno.py │ ├── prepare_lang.py │ └── prepare_lang_fst.py │ ├── prepare.sh │ ├── shared │ ├── tdnn │ ├── README.md │ ├── asr_datamodule.py │ ├── decode.py │ ├── export.py │ ├── export_onnx.py │ ├── jit_pretrained.py │ ├── jit_pretrained_decode_with_H.py │ ├── jit_pretrained_decode_with_HL.py │ ├── model.py │ ├── onnx_pretrained.py │ ├── pretrained.py │ └── train.py │ └── transducer │ ├── __init__.py │ ├── asr_datamodule.py │ ├── beam_search.py │ ├── decode.py │ ├── decoder.py │ ├── encoder.py │ ├── joiner.py │ ├── model.py │ ├── test_decoder.py │ ├── test_encoder.py │ ├── test_joiner.py │ ├── test_transducer.py │ └── train.py ├── icefall ├── __init__.py ├── ali.py ├── bpe_graph_compiler.py ├── byte_utils.py ├── char_graph_compiler.py ├── checkpoint.py ├── context_graph.py ├── ctc │ ├── .gitignore │ ├── README.md │ ├── __init__.py │ ├── prepare_lang.py │ ├── test_ctc_topo.py │ ├── test_prepare_lang.py │ ├── test_utils.py │ ├── topo.py │ └── utils.py ├── dataset │ ├── __init__.py │ └── datamodule.py ├── decode.py ├── diagnostics.py ├── dist.py ├── env.py ├── err.py ├── graph_compiler.py ├── hooks.py ├── lexicon.py ├── lm_wrapper.py ├── mmi.py ├── mmi_graph_compiler.py ├── ngram_lm.py ├── otc_graph_compiler.py ├── otc_phone_graph_compiler.py ├── profiler.py ├── rnn_lm │ ├── .gitignore │ ├── __init__.py │ ├── check-onnx-streaming.py │ ├── check-onnx.py │ ├── compute_perplexity.py │ ├── dataset.py │ ├── export-onnx.py │ ├── export-onnx.sh │ ├── export.py │ ├── export.sh │ ├── model.py │ ├── test_dataset.py │ ├── test_dataset_ddp.py │ ├── test_model.py │ └── train.py ├── shared │ ├── convert-k2-to-openfst.py │ ├── make_kn_lm.py │ ├── ngram_entropy_pruning.py │ └── parse_options.sh ├── transformer_lm │ ├── __init__.py │ ├── attention.py │ ├── compute_perplexity.py │ ├── dataset.py │ ├── encoder.py │ ├── export.py │ ├── model.py │ ├── scaling.py │ └── train.py └── utils.py ├── pyproject.toml ├── requirements-ci.txt ├── requirements-tts.txt ├── requirements.txt ├── setup.py └── test ├── test_ali.py ├── test_bpe_graph_compiler.py ├── test_checkpoint.py ├── test_ctc_greedy_search.py ├── test_decode.py ├── test_graph_compiler.py ├── test_lexicon.py ├── test_mmi_graph_compiler.py ├── test_ngram_lm.py ├── test_parse_timestamp.py └── test_utils.py /.github/scripts/.gitignore: -------------------------------------------------------------------------------- 1 | piper_phonemize.html 2 | -------------------------------------------------------------------------------- /docs/.gitignore: -------------------------------------------------------------------------------- 1 | build/ 2 | -------------------------------------------------------------------------------- /docs/requirements.txt: -------------------------------------------------------------------------------- 1 | sphinx_rtd_theme 2 | sphinx 3 | sphinxcontrib-youtube==1.1.0 4 | -------------------------------------------------------------------------------- /egs/aidatatang_200zh/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/aidatatang_200zh/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../egs/aishell/ASR/shared -------------------------------------------------------------------------------- /egs/aishell/ASR/conformer_ctc/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/aishell/ASR/conformer_ctc/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/aishell/ASR/conformer_mmi/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/aishell/ASR/conformer_mmi/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/aishell/ASR/local/compile_hlg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg.py -------------------------------------------------------------------------------- /egs/aishell/ASR/local/compile_lg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_lg.py -------------------------------------------------------------------------------- /egs/aishell/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/aishell/ASR/local/generate_unique_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/generate_unique_lexicon.py -------------------------------------------------------------------------------- /egs/aishell/ASR/local/prepare_lang_fst.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_fst.py -------------------------------------------------------------------------------- /egs/aishell/ASR/local/sort_lm_training_data.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/sort_lm_training_data.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless2/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless2/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless2/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/model.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless2/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless3/aidatatang_200zh.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless_modified-2/aidatatang_200zh.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless3/aishell.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless_modified-2/aishell.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless3/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless_modified-2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless3/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless3/lstmp.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless3/lstmp.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless3/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7/aishell.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/aishell.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless_modified-2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/beam_search.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/export.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/joiner.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/model.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7_bbpe/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7_bbpe/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7_streaming/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7_streaming/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/decoder.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7_streaming/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/joiner.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7_streaming/model.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/model.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7_streaming/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/aishell/ASR/pruned_transducer_stateless7_streaming/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling.py -------------------------------------------------------------------------------- /egs/aishell/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless/subsampling.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/subsampling.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified-2/conformer.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless_modified/conformer.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified-2/decoder.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless_modified/decoder.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified-2/joiner.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless_modified/joiner.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified-2/subsampling.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/subsampling.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified-2/test_decoder.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless_modified/test_decoder.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified-2/transformer.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless_modified/transformer.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified/conformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/conformer.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/decoder.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/joiner.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/model.py -------------------------------------------------------------------------------- /egs/aishell/ASR/transducer_stateless_modified/subsampling.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/subsampling.py -------------------------------------------------------------------------------- /egs/aishell/ASR/whisper/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/aishell/ASR/whisper/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/aishell/ASR/whisper/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decode_stream.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/encoder_interface.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/export-onnx-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-streaming.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/jit_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/jit_pretrained_streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained_streaming.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_check.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/onnx_pretrained-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained-streaming.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/streaming_beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/streaming_beam_search.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/aishell/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/aishell2/ASR/local/compile_lg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_lg.py -------------------------------------------------------------------------------- /egs/aishell2/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/aishell2/ASR/local/prepare_char.py: -------------------------------------------------------------------------------- 1 | ../../../aidatatang_200zh/ASR/local/prepare_char.py -------------------------------------------------------------------------------- /egs/aishell2/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../wenetspeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/aishell2/ASR/local/prepare_words.py: -------------------------------------------------------------------------------- 1 | ../../../wenetspeech/ASR/local/prepare_words.py -------------------------------------------------------------------------------- /egs/aishell2/ASR/local/text2segments.py: -------------------------------------------------------------------------------- 1 | ../../../wenetspeech/ASR/local/text2segments.py -------------------------------------------------------------------------------- /egs/aishell2/ASR/local/text2token.py: -------------------------------------------------------------------------------- 1 | ../../../aidatatang_200zh/ASR/local/text2token.py -------------------------------------------------------------------------------- /egs/aishell2/ASR/pruned_transducer_stateless5/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/aishell2/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/aishell4/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/aishell4/ASR/pruned_transducer_stateless5/local: -------------------------------------------------------------------------------- 1 | ../local -------------------------------------------------------------------------------- /egs/aishell4/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../egs/aishell/ASR/shared -------------------------------------------------------------------------------- /egs/alimeeting/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/alimeeting/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../egs/aishell/ASR/shared -------------------------------------------------------------------------------- /egs/alimeeting/ASR_v2/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/alimeeting/ASR_v2/local/prepare_char.py: -------------------------------------------------------------------------------- 1 | ../../ASR/local/prepare_char.py -------------------------------------------------------------------------------- /egs/alimeeting/ASR_v2/local/prepare_words.py: -------------------------------------------------------------------------------- 1 | ../../ASR/local/prepare_words.py -------------------------------------------------------------------------------- /egs/alimeeting/ASR_v2/local/text2segments.py: -------------------------------------------------------------------------------- 1 | ../../ASR/local/text2segments.py -------------------------------------------------------------------------------- /egs/alimeeting/ASR_v2/local/text2token.py: -------------------------------------------------------------------------------- 1 | ../../ASR/local/text2token.py -------------------------------------------------------------------------------- /egs/alimeeting/ASR_v2/shared: -------------------------------------------------------------------------------- 1 | ../../../egs/aishell/ASR/shared -------------------------------------------------------------------------------- /egs/ami/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/ami/ASR/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/ami/ASR/pruned_transducer_stateless7/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/export.py -------------------------------------------------------------------------------- /egs/ami/ASR/pruned_transducer_stateless7/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/joiner.py -------------------------------------------------------------------------------- /egs/ami/ASR/pruned_transducer_stateless7/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/model.py -------------------------------------------------------------------------------- /egs/ami/ASR/pruned_transducer_stateless7/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/ami/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/decoder.py -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/dprnn.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/dprnn.py -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/export.py -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/joiner.py -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/model.py -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/optim.py -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/scaling.py -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/ami/SURT/dprnn_zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../libricss/SURT/dprnn_zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/ami/SURT/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/ami/SURT/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/ami/SURT/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/audioset/AT/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/audioset/AT/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/audioset/AT/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/audioset/AT/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/audioset/AT/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/audioset/AT/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/audioset/AT/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/audioset/AT/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/baker_zh/TTS/.gitignore: -------------------------------------------------------------------------------- 1 | path.sh 2 | *.onnx 3 | *.wav 4 | generator_v1 5 | generator_v2 6 | generator_v3 7 | -------------------------------------------------------------------------------- /egs/baker_zh/TTS/local/audio.py: -------------------------------------------------------------------------------- 1 | ../matcha/audio.py -------------------------------------------------------------------------------- /egs/baker_zh/TTS/local/compute_fbank_statistics.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/local/compute_fbank_statistics.py -------------------------------------------------------------------------------- /egs/baker_zh/TTS/local/fbank.py: -------------------------------------------------------------------------------- 1 | ../matcha/fbank.py -------------------------------------------------------------------------------- /egs/baker_zh/TTS/matcha/audio.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/matcha/audio.py -------------------------------------------------------------------------------- /egs/baker_zh/TTS/matcha/export_onnx_hifigan.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/matcha/export_onnx_hifigan.py -------------------------------------------------------------------------------- /egs/baker_zh/TTS/matcha/fbank.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/matcha/fbank.py -------------------------------------------------------------------------------- /egs/baker_zh/TTS/matcha/hifigan: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/matcha/hifigan -------------------------------------------------------------------------------- /egs/baker_zh/TTS/matcha/model.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/matcha/model.py -------------------------------------------------------------------------------- /egs/baker_zh/TTS/matcha/models: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/matcha/models -------------------------------------------------------------------------------- /egs/baker_zh/TTS/matcha/monotonic_align: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/matcha/monotonic_align -------------------------------------------------------------------------------- /egs/baker_zh/TTS/matcha/utils.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/matcha/utils.py -------------------------------------------------------------------------------- /egs/baker_zh/TTS/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/commonvoice/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/local/filter_cuts.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/filter_cuts.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/local/prepare_char.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/local/prepare_char.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/local/prepare_lang_fst.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_fst.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/local/validate_bpe_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/validate_bpe_lexicon.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/pruned_transducer_stateless7_streaming/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/decoder.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/pruned_transducer_stateless7_streaming/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/joiner.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/pruned_transducer_stateless7_streaming/model.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/model.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/pruned_transducer_stateless7_streaming/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/pruned_transducer_stateless7_streaming/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/asr_datamodule.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decode_stream.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/export-onnx-ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-ctc.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/export-onnx-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-streaming.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_check.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/streaming_beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/streaming_beam_search.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/commonvoice/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/csj/ASR/pruned_transducer_stateless7_streaming/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../local/utils/asr_datamodule.py -------------------------------------------------------------------------------- /egs/csj/ASR/pruned_transducer_stateless7_streaming/tokenizer.py: -------------------------------------------------------------------------------- 1 | ../local/utils/tokenizer.py -------------------------------------------------------------------------------- /egs/csj/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/fluent_speech_commands/SLU/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/fluent_speech_commands/SLU/transducer/conformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/conformer.py -------------------------------------------------------------------------------- /egs/fluent_speech_commands/SLU/transducer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../yesno/ASR/transducer/decoder.py -------------------------------------------------------------------------------- /egs/fluent_speech_commands/SLU/transducer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer/joiner.py -------------------------------------------------------------------------------- /egs/fluent_speech_commands/SLU/transducer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer/model.py -------------------------------------------------------------------------------- /egs/fluent_speech_commands/SLU/transducer/test_conformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer/test_conformer.py -------------------------------------------------------------------------------- /egs/fluent_speech_commands/SLU/transducer/test_decoder.py: -------------------------------------------------------------------------------- 1 | ../../../yesno/ASR/transducer/test_decoder.py -------------------------------------------------------------------------------- /egs/fluent_speech_commands/SLU/transducer/test_joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer/test_joiner.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/.gitignore: -------------------------------------------------------------------------------- 1 | log-* 2 | .DS_Store -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/local/compile_hlg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/local/generate_unique_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/generate_unique_lexicon.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/pruned_transducer_stateless2/gigaspeech_scoring.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/gigaspeech_scoring.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decode_stream.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/export-onnx-ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-ctc.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/export-onnx-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-streaming.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/gigaspeech_scoring.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/gigaspeech_scoring.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/jit_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/jit_pretrained_ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained_ctc.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/my_profile.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/my_profile.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_check.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/onnx_decode.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_decode.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/onnx_pretrained_ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained_ctc.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/onnx_pretrained_ctc_H.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained_ctc_H.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/pretrained_ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained_ctc.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/streaming_beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/streaming_beam_search.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/test_scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/test_scaling.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/test_subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/test_subsampling.py -------------------------------------------------------------------------------- /egs/gigaspeech/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/export-onnx-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-streaming.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/gigaspeech_scoring.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/gigaspeech_scoring.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/gigaspeech/KWS/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/local/filter_cuts.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/filter_cuts.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/local/validate_manifest.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/validate_manifest.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7_streaming/asr_datamodule.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decode_stream.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/export-onnx-ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-ctc.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/export-onnx-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-streaming.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_check.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/onnx_decode.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_decode.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/onnx_pretrained_ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained_ctc.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/pretrained_ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained_ctc.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/streaming_beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/streaming_beam_search.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/test_scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/test_scaling.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/test_subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/test_subsampling.py -------------------------------------------------------------------------------- /egs/ksponspeech/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/libricss/SURT/dprnn_zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/decoder.py -------------------------------------------------------------------------------- /egs/libricss/SURT/dprnn_zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/joiner.py -------------------------------------------------------------------------------- /egs/libricss/SURT/dprnn_zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/libricss/SURT/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/libriheavy/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/jit_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/onnx_decode.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_decode.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/scaling_coverter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/libriheavy/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/dataset.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/dataset.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/hubert_ce.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/hubert_ce.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/model.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/optim.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/utils.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/utils.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/wav2vec2_module.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/wav2vec2_module.py -------------------------------------------------------------------------------- /egs/librilight/SSL/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/SSL/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/.gitignore: -------------------------------------------------------------------------------- 1 | log-* 2 | .DS_Store 3 | run*.sh 4 | -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc2/__init__.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/__init__.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc2/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc2/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc2/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc2/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc3/__init__.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/__init__.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc3/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc3/conformer.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/conformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc3/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc3/lstmp.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/lstmp.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc3/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc3/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_ctc3/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/scaling_converter.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conformer_mmi/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conv_emformer_transducer_stateless/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conv_emformer_transducer_stateless/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conv_emformer_transducer_stateless/model.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conv_emformer_transducer_stateless/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conv_emformer_transducer_stateless/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conv_emformer_transducer_stateless2/joiner.py: -------------------------------------------------------------------------------- 1 | ../conv_emformer_transducer_stateless/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conv_emformer_transducer_stateless2/lstmp.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/lstmp.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conv_emformer_transducer_stateless2/model.py: -------------------------------------------------------------------------------- 1 | ../conv_emformer_transducer_stateless/model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conv_emformer_transducer_stateless2/optim.py: -------------------------------------------------------------------------------- 1 | ../conv_emformer_transducer_stateless/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/conv_emformer_transducer_stateless2/stream.py: -------------------------------------------------------------------------------- 1 | ../conv_emformer_transducer_stateless/stream.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/local/sort_lm_training_data.py: -------------------------------------------------------------------------------- 1 | ../../../ptb/LM/local/sort_lm_training_data.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/__init__.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/__init__.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/export-onnx.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/lstmp.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/lstmp.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/onnx_check.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless2/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless2/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless2/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless2/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless2/gigaspeech.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/gigaspeech.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless2/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless2/librispeech.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/librispeech.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless2/lstm.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless/lstm.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless2/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless2/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/__init__.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/__init__.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/export-for-ncnn.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/export-for-ncnn.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/export-onnx.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/lstmp.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/lstmp.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/model.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless/model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/onnx_check.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/lstm_transducer_stateless3/stream.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless/stream.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_stateless_emformer_rnnt2/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_stateless_emformer_rnnt2/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_stateless_emformer_rnnt2/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_stateless_emformer_rnnt2/subsampling.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../transducer/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless/conformer.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/conformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/onnx_check.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless/subsampling.py: -------------------------------------------------------------------------------- 1 | ../transducer/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless/transformer.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/transformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless2/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../transducer/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless2/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless/decode_stream.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless2/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless2/lstmp.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/lstmp.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless2/test_model.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless/test_model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless3/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless3/conformer.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/conformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless3/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless/decode_stream.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless3/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless3/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless3/lstmp.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/lstmp.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless3/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless3/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless3/test_model.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless/test_model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/__init__.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/__init__.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/conformer.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/conformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless/decode_stream.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/lstmp.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/lstmp.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/model.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless4/test_model.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless/test_model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless5/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless5/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless/decode_stream.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless5/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless5/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless5/lstmp.py: -------------------------------------------------------------------------------- 1 | ../lstm_transducer_stateless2/lstmp.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless5/model.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless5/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/onnx_check.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless5/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless5/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless6/__init__.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/__init__.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless6/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless6/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless6/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless6/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless6/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless5/onnx_check.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc/zipformer.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/zipformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc_bs/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc_bs/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc_bs/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc_bs/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_ctc_bs/zipformer.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/zipformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_streaming/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_streaming/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_streaming/model.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_streaming/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless7_streaming/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless8/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless8/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless8/gigaspeech.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/gigaspeech.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless8/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless8/librispeech.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless3/librispeech.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless8/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless8/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/pruned_transducer_stateless8/zipformer.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/zipformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/librispeech/ASR/streaming_conformer_ctc/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/streaming_conformer_ctc/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/streaming_conformer_ctc/subsampling.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/tiny_transducer_ctc/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/tiny_transducer_ctc/decoder.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/tiny_transducer_ctc/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/tiny_transducer_ctc/joiner.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/tiny_transducer_ctc/model.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7_ctc/model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/tiny_transducer_ctc/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer/conformer.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/conformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer/transformer.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/transformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_lstm/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../transducer/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_lstm/subsampling.py: -------------------------------------------------------------------------------- 1 | ../transducer/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../transducer/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless/subsampling.py: -------------------------------------------------------------------------------- 1 | ../transducer/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless2/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless2/beam_search.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless2/conformer.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/conformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless2/decoder.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless2/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless2/subsampling.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless2/transformer.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/transformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless_multi_datasets/beam_search.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless_multi_datasets/conformer.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/conformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless_multi_datasets/decoder.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless_multi_datasets/joiner.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless_multi_datasets/subsampling.py: -------------------------------------------------------------------------------- 1 | ../transducer/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/transducer_stateless_multi_datasets/transformer.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/transformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer/.gitignore: -------------------------------------------------------------------------------- 1 | swoosh.pdf 2 | -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../transducer/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/decoder.py: -------------------------------------------------------------------------------- 1 | ../zipformer/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/joiner.py: -------------------------------------------------------------------------------- 1 | ../zipformer/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/model.py: -------------------------------------------------------------------------------- 1 | ../zipformer/model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/optim.py: -------------------------------------------------------------------------------- 1 | ../zipformer/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/scaling.py: -------------------------------------------------------------------------------- 1 | ../zipformer/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_adapter/subsampling.py: -------------------------------------------------------------------------------- 1 | ../zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_ctc/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_ctc/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_ctc/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_ctc/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_ctc/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_ctc/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling_converter.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_ctc/subsampling.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_ctc/transformer.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/transformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_ctc/zipformer.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/zipformer.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_lora/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_lora/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_lora/decoder.py: -------------------------------------------------------------------------------- 1 | ../zipformer/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_lora/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_lora/joiner.py: -------------------------------------------------------------------------------- 1 | ../zipformer/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_lora/model.py: -------------------------------------------------------------------------------- 1 | ../zipformer/model.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_lora/optim.py: -------------------------------------------------------------------------------- 1 | ../zipformer/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_lora/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_lora/subsampling.py: -------------------------------------------------------------------------------- 1 | ../zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_mmi/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_mmi/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_mmi/optim.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/optim.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_mmi/scaling.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_mmi/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/scaling_converter.py -------------------------------------------------------------------------------- /egs/librispeech/ASR/zipformer_mmi/zipformer.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless7/zipformer.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/hubert/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/hubert/decoder.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/hubert/joiner.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/hubert/optim.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/hubert/scaling.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/librispeech/SSL/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../hubert/asr_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/zipformer/dataset.py: -------------------------------------------------------------------------------- 1 | ../hubert/dataset.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/SSL/zipformer/ssl_datamodule.py: -------------------------------------------------------------------------------- 1 | ../hubert/ssl_datamodule.py -------------------------------------------------------------------------------- /egs/librispeech/WSASR/conformer_ctc2/__init__.py: -------------------------------------------------------------------------------- 1 | ../../ASR/pruned_transducer_stateless2/__init__.py -------------------------------------------------------------------------------- /egs/librispeech/WSASR/conformer_ctc2/attention.py: -------------------------------------------------------------------------------- 1 | ../../ASR/conformer_ctc2/attention.py -------------------------------------------------------------------------------- /egs/librispeech/WSASR/conformer_ctc2/export.py: -------------------------------------------------------------------------------- 1 | ../../ASR/conformer_ctc2/export.py -------------------------------------------------------------------------------- /egs/librispeech/WSASR/conformer_ctc2/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../ASR/conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/librispeech/WSASR/conformer_ctc2/optim.py: -------------------------------------------------------------------------------- 1 | ../../ASR/pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/librispeech/WSASR/conformer_ctc2/scaling.py: -------------------------------------------------------------------------------- 1 | ../../ASR/pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/librispeech/WSASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/libritts/ASR/local/compile_hlg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg.py -------------------------------------------------------------------------------- /egs/libritts/ASR/local/compile_lg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_lg.py -------------------------------------------------------------------------------- /egs/libritts/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/libritts/ASR/local/download_lm.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/download_lm.py -------------------------------------------------------------------------------- /egs/libritts/ASR/local/norm_text.py: -------------------------------------------------------------------------------- 1 | ../../../libriheavy/ASR/local/norm_text.py -------------------------------------------------------------------------------- /egs/libritts/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/libritts/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/libritts/ASR/local/prepare_lang_fst.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_fst.py -------------------------------------------------------------------------------- /egs/libritts/ASR/local/prepare_lm_training_data.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lm_training_data.py -------------------------------------------------------------------------------- /egs/libritts/ASR/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/libritts/ASR/local/validate_bpe_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/validate_bpe_lexicon.py -------------------------------------------------------------------------------- /egs/libritts/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/.gitignore: -------------------------------------------------------------------------------- 1 | swoosh.pdf 2 | -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/attention_decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/attention_decoder.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decode_stream.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/export-onnx-ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-ctc.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/export-onnx-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-streaming.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/jit_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/jit_pretrained_ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained_ctc.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/label_smoothing.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/my_profile.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/my_profile.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_check.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/onnx_pretrained_ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained_ctc.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/onnx_pretrained_ctc_H.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained_ctc_H.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/onnx_pretrained_ctc_HL.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained_ctc_HL.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/pretrained_ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained_ctc.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/streaming_beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/streaming_beam_search.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/libritts/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/libritts/CODEC/encodec/utils.py: -------------------------------------------------------------------------------- 1 | ../../../vctk/TTS/vits/utils.py -------------------------------------------------------------------------------- /egs/libritts/CODEC/local/validate_manifest.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/local/validate_manifest.py -------------------------------------------------------------------------------- /egs/libritts/CODEC/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/libritts/TTS/local/compute_spectrogram_libritts.py: -------------------------------------------------------------------------------- 1 | ../../CODEC/local/compute_spectrogram_libritts.py -------------------------------------------------------------------------------- /egs/libritts/TTS/local/prepare_token_file.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/local/prepare_token_file.py -------------------------------------------------------------------------------- /egs/libritts/TTS/local/validate_manifest.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/local/validate_manifest.py -------------------------------------------------------------------------------- /egs/libritts/TTS/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/libritts/TTS/valle: -------------------------------------------------------------------------------- 1 | ../../wenetspeech4tts/TTS/valle/ -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/duration_predictor.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/duration_predictor.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/flow.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/flow.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/generator.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/generator.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/hifigan.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/hifigan.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/loss.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/loss.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/monotonic_align: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/monotonic_align -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/posterior_encoder.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/posterior_encoder.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/residual_coupling.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/residual_coupling.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/text_encoder.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/text_encoder.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/tokenizer.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/tokenizer.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/transform.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/transform.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/utils.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/utils.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/vits.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/vits.py -------------------------------------------------------------------------------- /egs/libritts/TTS/vits/wavenet.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/wavenet.py -------------------------------------------------------------------------------- /egs/ljspeech/TTS/.gitignore: -------------------------------------------------------------------------------- 1 | build 2 | core.c 3 | *.so 4 | my-output* 5 | *.wav 6 | *.onnx 7 | generator_v* 8 | -------------------------------------------------------------------------------- /egs/ljspeech/TTS/local/audio.py: -------------------------------------------------------------------------------- 1 | ../matcha/audio.py -------------------------------------------------------------------------------- /egs/ljspeech/TTS/local/fbank.py: -------------------------------------------------------------------------------- 1 | ../matcha/fbank.py -------------------------------------------------------------------------------- /egs/ljspeech/TTS/matcha/monotonic_align/.gitignore: -------------------------------------------------------------------------------- 1 | build 2 | core.c 3 | *.so -------------------------------------------------------------------------------- /egs/ljspeech/TTS/matcha/tokenizer.py: -------------------------------------------------------------------------------- 1 | ../vits/tokenizer.py -------------------------------------------------------------------------------- /egs/ljspeech/TTS/matcha/utils.py: -------------------------------------------------------------------------------- 1 | ../vits/utils.py -------------------------------------------------------------------------------- /egs/ljspeech/TTS/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/ljspeech/TTS/vits/monotonic_align/.gitignore: -------------------------------------------------------------------------------- 1 | build 2 | core.c 3 | *.so -------------------------------------------------------------------------------- /egs/mdcc/ASR/local/compile_hlg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/local/compile_hlg_using_openfst.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg_using_openfst.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/local/compile_lg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_lg.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/local/prepare_char.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/local/prepare_char.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/local/prepare_char_lm_training_data.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/local/prepare_char_lm_training_data.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/local/prepare_lang_fst.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_fst.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/local/text2token.py: -------------------------------------------------------------------------------- 1 | ../../../aidatatang_200zh/ASR/local/text2token.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decode_stream.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/export-onnx-ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-ctc.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/export-onnx-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-streaming.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_check.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/streaming_beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/streaming_beam_search.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/mdcc/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/compile_hlg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/conformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/conformer.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/download_lm.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/download_lm.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/export.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/generate_unique_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/generate_unique_lexicon.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/subsampling.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/test_label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/test_label_smoothing.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/test_subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/test_subsampling.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/test_transformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/test_transformer.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/conformer_ctc/transformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/transformer.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/local/compile_hlg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/local/generate_unique_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/generate_unique_lexicon.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/local/test_prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/test_prepare_lang.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/pruned_transducer_stateless5/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../conformer_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/pruned_transducer_stateless5/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless5/model.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/pruned_transducer_stateless5/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless5/optim.py -------------------------------------------------------------------------------- /egs/mgb2/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/local/prepare_char.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/local/prepare_char.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/local/prepare_words.py: -------------------------------------------------------------------------------- 1 | ../../../aishell2/ASR/local/prepare_words.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/local/validate_bpe_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/validate_bpe_lexicon.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../local/utils/asr_datamodule.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/ctc_decode.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/ctc_decode.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decode_stream.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/my_profile.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/my_profile.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/onnx_decode.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_decode.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/streaming_beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/streaming_beam_search.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/test_scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/test_scaling.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/test_subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/test_subsampling.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/tokenizer.py: -------------------------------------------------------------------------------- 1 | ../local/utils/tokenizer.py -------------------------------------------------------------------------------- /egs/multi_ja_en/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/local/compile_lg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_lg.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/local/prepare_char.py: -------------------------------------------------------------------------------- 1 | ../../../wenetspeech/ASR/local/prepare_char.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/local/text2token.py: -------------------------------------------------------------------------------- 1 | ../../../wenetspeech/ASR/local/text2token.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/local/validate_bpe_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/validate_bpe_lexicon.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/whisper/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../zipformer/asr_datamodule.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/whisper/ds_config_zero1.json: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/whisper/ds_config_zero1.json -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/whisper/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/whisper/multi_dataset.py: -------------------------------------------------------------------------------- 1 | ../../../speech_llm/ASR_LLM/whisper_llm_zh/multi_dataset.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/whisper/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/whisper/requirements.txt: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/whisper/requirements.txt -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/jit_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/jit_pretrained_ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained_ctc.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/multi_dataset.py: -------------------------------------------------------------------------------- 1 | ../../../speech_llm/ASR_LLM/whisper_llm_zh/multi_dataset.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_check.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/onnx_decode.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_decode.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/streaming_decode.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/streaming_decode.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/multi_zh-hans/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/local/compile_lg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_lg.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/local/prepare_char.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/local/prepare_char.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/local/prepare_lang_bbpe.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/local/prepare_lang_bbpe.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/local/prepare_words.py: -------------------------------------------------------------------------------- 1 | ../../../aishell2/ASR/local/prepare_words.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/local/text2segments.py: -------------------------------------------------------------------------------- 1 | ../../../wenetspeech/ASR/local/text2segments.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/local/text2token.py: -------------------------------------------------------------------------------- 1 | ../../../wenetspeech/ASR/local/text2token.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/local/train_bbpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/local/train_bbpe_model.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/local/validate_bpe_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/validate_bpe_lexicon.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decode_stream.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/export-onnx-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-streaming.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/jit_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/jit_pretrained_ctc.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained_ctc.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_check.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/onnx_decode.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_decode.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/streaming_beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/streaming_beam_search.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/multi_zh_en/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/must_c/ST/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/must_c/ST/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/must_c/ST/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/must_c/ST/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/must_c/ST/local/validate_bpe_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/validate_bpe_lexicon.py -------------------------------------------------------------------------------- /egs/must_c/ST/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/ptb/LM/local/prepare_lm_training_data.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lm_training_data.py -------------------------------------------------------------------------------- /egs/ptb/LM/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/ptb/LM/rnn_lm: -------------------------------------------------------------------------------- 1 | ../../../icefall/rnn_lm -------------------------------------------------------------------------------- /egs/ptb/LM/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../local/utils/asr_datamodule.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/ctc_decode.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/ctc_decode.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decode_stream.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/my_profile.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/my_profile.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/test_scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/test_scaling.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/test_subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/test_subsampling.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/tokenizer.py: -------------------------------------------------------------------------------- 1 | ../local/utils/tokenizer.py -------------------------------------------------------------------------------- /egs/reazonspeech/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/speech_llm/ASR_LLM/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/speech_llm/ASR_LLM/whisper_llm_zh/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../../../multi_zh-hans/ASR/zipformer/asr_datamodule.py -------------------------------------------------------------------------------- /egs/speech_llm/ASR_LLM/whisper_llm_zh/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/speechio/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared// -------------------------------------------------------------------------------- /egs/speechio/ASR/whisper/requirements.txt: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/whisper/requirements.txt -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../whisper/asr_datamodule.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/beam_search.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/encoder_interface.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/multi_dataset.py: -------------------------------------------------------------------------------- 1 | ../whisper/multi_dataset.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/train.py: -------------------------------------------------------------------------------- 1 | ../../../multi_zh-hans/ASR/zipformer/train.py -------------------------------------------------------------------------------- /egs/speechio/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/local/compile_hlg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/spgispeech/ASR/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/spgispeech/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/swbd/ASR/.gitignore: -------------------------------------------------------------------------------- 1 | switchboard_word_alignments.tar.gz 2 | ./swb_ms98_transcriptions/ 3 | -------------------------------------------------------------------------------- /egs/swbd/ASR/conformer_ctc/conformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/conformer.py -------------------------------------------------------------------------------- /egs/swbd/ASR/conformer_ctc/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/swbd/ASR/conformer_ctc/pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/pretrained.py -------------------------------------------------------------------------------- /egs/swbd/ASR/conformer_ctc/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/subsampling.py -------------------------------------------------------------------------------- /egs/swbd/ASR/conformer_ctc/test_transformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/test_transformer.py -------------------------------------------------------------------------------- /egs/swbd/ASR/conformer_ctc/transformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/transformer.py -------------------------------------------------------------------------------- /egs/swbd/ASR/local/compile_hlg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg.py -------------------------------------------------------------------------------- /egs/swbd/ASR/local/compile_lg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_lg.py -------------------------------------------------------------------------------- /egs/swbd/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/swbd/ASR/local/prepare_lm_training_data.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lm_training_data.py -------------------------------------------------------------------------------- /egs/swbd/ASR/local/validate_bpe_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/validate_bpe_lexicon.py -------------------------------------------------------------------------------- /egs/swbd/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/tal_csasr/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/tal_csasr/ASR/local/train_bbpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/local/train_bbpe_model.py -------------------------------------------------------------------------------- /egs/tal_csasr/ASR/pruned_transducer_stateless7_bbpe/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless5/beam_search.py -------------------------------------------------------------------------------- /egs/tal_csasr/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../librispeech/ASR/shared -------------------------------------------------------------------------------- /egs/tedlium3/ASR/conformer_ctc2/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/asr_datamodule.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/conformer_ctc2/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/conformer_ctc2/local: -------------------------------------------------------------------------------- 1 | ../local -------------------------------------------------------------------------------- /egs/tedlium3/ASR/conformer_ctc2/lstmp.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/lstm_transducer_stateless2/lstmp.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/conformer_ctc2/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/optim.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/conformer_ctc2/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/scaling.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/conformer_ctc2/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc2/subsampling.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/local/compile_hlg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/pruned_transducer_stateless/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/asr_datamodule.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/pruned_transducer_stateless/local: -------------------------------------------------------------------------------- 1 | ../local -------------------------------------------------------------------------------- /egs/tedlium3/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/tedlium3/ASR/transducer_stateless/conformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/conformer.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/transducer_stateless/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/joiner.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/transducer_stateless/local: -------------------------------------------------------------------------------- 1 | ../local -------------------------------------------------------------------------------- /egs/tedlium3/ASR/transducer_stateless/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/model.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/transducer_stateless/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/subsampling.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/transducer_stateless/transformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/transformer.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../transducer_stateless/asr_datamodule.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/transducer_stateless/encoder_interface.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/local: -------------------------------------------------------------------------------- 1 | ../local -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/my_profile.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/my_profile.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/tedlium3/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/timit/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/timit/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/timit/ASR/tdnn_ligru_ctc/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/vctk/TTS/local/prepare_token_file.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/local/prepare_token_file.py -------------------------------------------------------------------------------- /egs/vctk/TTS/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/duration_predictor.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/duration_predictor.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/flow.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/flow.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/generator.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/generator.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/hifigan.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/hifigan.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/loss.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/loss.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/monotonic_align: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/monotonic_align -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/posterior_encoder.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/posterior_encoder.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/residual_coupling.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/residual_coupling.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/text_encoder.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/text_encoder.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/tokenizer.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/tokenizer.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/transform.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/transform.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/utils.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/utils.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/vits.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/vits.py -------------------------------------------------------------------------------- /egs/vctk/TTS/vits/wavenet.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/vits/wavenet.py -------------------------------------------------------------------------------- /egs/voxpopuli/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/voxpopuli/ASR/local/filter_cuts.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/filter_cuts.py -------------------------------------------------------------------------------- /egs/voxpopuli/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/voxpopuli/ASR/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/voxpopuli/ASR/local/validate_bpe_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/validate_bpe_lexicon.py -------------------------------------------------------------------------------- /egs/voxpopuli/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/local/compile_lg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_lg.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/local/sort_lm_training_data.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/local/sort_lm_training_data.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/pruned_transducer_stateless2/aishell.py: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/tdnn_lstm_ctc/asr_datamodule.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../librispeech/ASR/shared -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/whisper/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/whisper/ds_config_zero1.json: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/whisper/ds_config_zero1.json -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/whisper/label_smoothing.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/conformer_ctc/label_smoothing.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/whisper/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/whisper/requirements.txt: -------------------------------------------------------------------------------- 1 | ../../../aishell/ASR/whisper/requirements.txt -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/asr_datamodule.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/decode_stream.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decode_stream.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../pruned_transducer_stateless2/encoder_interface.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/export-onnx-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-streaming.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/export-onnx.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/jit_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/jit_pretrained.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/onnx_check.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_check.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/onnx_pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/onnx_pretrained.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/pretrained.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/pretrained.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/streaming_beam_search.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/streaming_beam_search.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/wenetspeech/ASR/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/beam_search.py: -------------------------------------------------------------------------------- 1 | ../../ASR/pruned_transducer_stateless2/beam_search.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/decoder.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/decoder.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/encoder_interface.py: -------------------------------------------------------------------------------- 1 | ../../ASR/pruned_transducer_stateless2/encoder_interface.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/export-onnx-streaming.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export-onnx-streaming.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/export.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/export.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/joiner.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/joiner.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/model.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/scaling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/scaling_converter.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/scaling_converter.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/subsampling.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/subsampling.py -------------------------------------------------------------------------------- /egs/wenetspeech/KWS/zipformer/zipformer.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/zipformer.py -------------------------------------------------------------------------------- /egs/wenetspeech4tts/TTS/f5-tts/utils.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/matcha/utils.py -------------------------------------------------------------------------------- /egs/wenetspeech4tts/TTS/local/fbank.py: -------------------------------------------------------------------------------- 1 | ../../../ljspeech/TTS/matcha/fbank.py -------------------------------------------------------------------------------- /egs/wenetspeech4tts/TTS/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/wenetspeech4tts/TTS/valle/optim.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/zipformer/optim.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/compile_hlg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_hlg.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/compile_lg.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compile_lg.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/compute_fbank_musan.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/compute_fbank_musan.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/filter_cuts.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/filter_cuts.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/generate_unique_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/generate_unique_lexicon.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/prepare_lang.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/prepare_lang_bpe.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_bpe.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/prepare_lm_training_data.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lm_training_data.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/sort_lm_training_data.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/sort_lm_training_data.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/train_bpe_model.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/train_bpe_model.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/local/validate_bpe_lexicon.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/validate_bpe_lexicon.py -------------------------------------------------------------------------------- /egs/xbmu_amdo31/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/yesno/ASR/local/prepare_lang_fst.py: -------------------------------------------------------------------------------- 1 | ../../../librispeech/ASR/local/prepare_lang_fst.py -------------------------------------------------------------------------------- /egs/yesno/ASR/shared: -------------------------------------------------------------------------------- 1 | ../../../icefall/shared/ -------------------------------------------------------------------------------- /egs/yesno/ASR/transducer/asr_datamodule.py: -------------------------------------------------------------------------------- 1 | ../tdnn/asr_datamodule.py -------------------------------------------------------------------------------- /icefall/ctc/.gitignore: -------------------------------------------------------------------------------- 1 | *.pdf 2 | *.gv 3 | -------------------------------------------------------------------------------- /icefall/rnn_lm/.gitignore: -------------------------------------------------------------------------------- 1 | icefall-librispeech-rnn-lm 2 | -------------------------------------------------------------------------------- /icefall/transformer_lm/dataset.py: -------------------------------------------------------------------------------- 1 | ../rnn_lm/dataset.py -------------------------------------------------------------------------------- /icefall/transformer_lm/scaling.py: -------------------------------------------------------------------------------- 1 | ../../egs/librispeech/ASR/pruned_transducer_stateless2/scaling.py --------------------------------------------------------------------------------