├── .gitignore ├── LICENSE ├── README.md ├── api_judge.py ├── evaluate.py ├── main.py ├── requirements.txt └── src ├── __init__.py ├── api ├── __init__.py └── gpt.py ├── evaluator ├── __init__.py ├── base.py ├── bbh.py ├── harm.py ├── ifeval.py ├── instruction_following_eval │ ├── README.md │ ├── __init__.py │ ├── instructions.py │ ├── instructions_registry.py │ └── instructions_util.py ├── mcq.py ├── open.py └── qa.py └── models ├── __init__.py ├── baichuan.py ├── base.py ├── diva.py ├── freeze_omni.py ├── glm.py ├── gpt4o.py ├── ichigo.py ├── lyra.py ├── megrez.py ├── meralion.py ├── mini_omni.py ├── mini_omni2.py ├── minicpm.py ├── moshi.py ├── naive.py ├── naive2.py ├── naive3.py ├── naive4.py ├── phi.py ├── qwen2.py ├── qwen_omni.py ├── src_freeze_omni ├── __init__.py ├── adapter.py ├── audioLLM.py ├── decoder │ ├── decoder.py │ ├── llm2tts.py │ └── ticodec │ │ ├── models.py │ │ ├── vqvae.py │ │ └── vqvae_tester.py ├── encoder │ ├── __init__.py │ ├── attention.py │ ├── cmvn.py │ ├── encoder.py │ ├── subsampling.py │ └── transformer.py ├── masks.py ├── pipeline.py └── utils.py ├── src_glm ├── __init__.py └── speech_tokenizer │ ├── __init__.py │ ├── configuration_whisper.py │ ├── generation_whisper.py │ ├── modeling_whisper.py │ └── utils.py ├── src_lyra ├── __init__.py ├── constants.py ├── conversation.py ├── mm_utils.py ├── model │ ├── __init__.py │ ├── builder.py │ ├── language_model │ │ ├── lyra_qwen2vl.py │ │ ├── lyra_qwen2vl_extractor.py │ │ └── lyra_qwen2vl_speechgenerator.py │ ├── lyra_arch_qwen2vl.py │ ├── lyra_arch_qwen2vl_extractor.py │ ├── multimodal_encoder │ │ ├── builder.py │ │ ├── clip_encoder.py │ │ ├── eva_encoder.py │ │ ├── imagebind │ │ │ ├── data.py │ │ │ ├── helpers.py │ │ │ ├── imagebind_model.py │ │ │ ├── multimodal_preprocessors.py │ │ │ └── transformer.py │ │ ├── imagebind_encoder.py │ │ ├── intern_vit_6b │ │ │ ├── configuration_intern_vit.py │ │ │ ├── flash_attention.py │ │ │ └── modeling_intern_vit.py │ │ ├── openclip_encoder.py │ │ ├── qwen2vl_encoder.py │ │ ├── siglip_encoder.py │ │ └── whisper_encoder.py │ ├── multimodal_generator │ │ ├── builder.py │ │ ├── generation.py │ │ └── speech_generator.py │ ├── multimodal_projector │ │ └── builder.py │ ├── qwen2vl_top_attn.py │ └── soft_dtw_cuda.py └── utils.py ├── src_mini_omni ├── LICENSE ├── README.md ├── __init__.py ├── litgpt │ ├── __init__.py │ ├── config.py │ ├── generate │ │ ├── __init__.py │ │ └── base.py │ ├── model.py │ ├── tokenizer.py │ └── utils.py ├── requirements.txt └── utils │ ├── __init__.py │ ├── assets │ └── silero_vad.onnx │ ├── snac_utils.py │ └── vad.py ├── src_mini_omni2 ├── LICENSE ├── README.md ├── __init__.py ├── inference.py ├── litgpt │ ├── __init__.py │ ├── config.py │ ├── generate │ │ ├── __init__.py │ │ └── base.py │ ├── model.py │ ├── tokenizer.py │ └── utils.py └── utils │ ├── __init__.py │ ├── assets │ └── silero_vad.onnx │ ├── snac_utils.py │ └── vad.py ├── src_step_audio ├── LICENSE ├── README.md ├── README_CN.md ├── __init__.py ├── app.py ├── assets │ ├── Step-Audio.pdf │ ├── architecture.png │ ├── logo.png │ ├── pipeline.png │ ├── rlhf.png │ ├── stepeval_radar_chart.png │ └── yuewen.jpeg ├── cosyvoice │ ├── __init__.py │ ├── cli │ │ ├── __init__.py │ │ ├── cosyvoice.py │ │ ├── frontend.py │ │ └── model.py │ ├── flow │ │ ├── decoder.py │ │ ├── flow.py │ │ ├── flow_matching.py │ │ └── length_regulator.py │ ├── hifigan │ │ ├── f0_predictor.py │ │ └── generator.py │ ├── matcha │ │ ├── audio.py │ │ ├── decoder.py │ │ ├── flow_matching.py │ │ └── transformer.py │ ├── transformer │ │ ├── __init__.py │ │ ├── activation.py │ │ ├── attention.py │ │ ├── convolution.py │ │ ├── decoder.py │ │ ├── decoder_layer.py │ │ ├── embedding.py │ │ ├── encoder.py │ │ ├── encoder_layer.py │ │ ├── label_smoothing_loss.py │ │ ├── positionwise_feed_forward.py │ │ └── subsampling.py │ └── utils │ │ ├── __init__.py │ │ ├── audio.py │ │ ├── class_utils.py │ │ ├── common.py │ │ ├── executor.py │ │ ├── file_utils.py │ │ ├── frontend_utils.py │ │ ├── mask.py │ │ ├── scheduler.py │ │ └── train_utils.py ├── funasr_detach │ ├── __init__.py │ ├── auto │ │ ├── __init__.py │ │ ├── auto_frontend.py │ │ ├── auto_model.py │ │ └── auto_tokenizer.py │ ├── bin │ │ ├── __init__.py │ │ ├── compute_audio_cmvn.py │ │ ├── inference.py │ │ ├── tokenize_text.py │ │ └── train.py │ ├── datasets │ │ ├── __init__.py │ │ └── audio_datasets │ │ │ ├── __init__.py │ │ │ ├── datasets.py │ │ │ ├── index_ds.py │ │ │ ├── preprocessor.py │ │ │ ├── samplers.py │ │ │ └── scp2jsonl.py │ ├── download │ │ ├── __init__.py │ │ ├── download_dataset_from_hub.py │ │ ├── download_from_hub.py │ │ ├── file.py │ │ ├── name_maps_from_hub.py │ │ └── runtime_sdk_download_tool.py │ ├── frontends │ │ ├── __init__.py │ │ ├── default.py │ │ ├── eend_ola_feature.py │ │ ├── fused.py │ │ ├── s3prl.py │ │ ├── utils │ │ │ ├── __init__.py │ │ │ ├── beamformer.py │ │ │ ├── complex_utils.py │ │ │ ├── dnn_beamformer.py │ │ │ ├── dnn_wpe.py │ │ │ ├── feature_transform.py │ │ │ ├── frontend.py │ │ │ ├── log_mel.py │ │ │ ├── mask_estimator.py │ │ │ └── stft.py │ │ ├── wav_frontend.py │ │ └── windowing.py │ ├── losses │ │ ├── __init__.py │ │ └── label_smoothing_loss.py │ ├── metrics │ │ ├── __init__.py │ │ ├── common.py │ │ ├── compute_acc.py │ │ ├── compute_eer.py │ │ ├── compute_min_dcf.py │ │ └── compute_wer.py │ ├── models │ │ ├── __init__.py │ │ ├── bat │ │ │ ├── __init__.py │ │ │ └── model.py │ │ ├── bicif_paraformer │ │ │ ├── __init__.py │ │ │ ├── cif_predictor.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── branchformer │ │ │ ├── __init__.py │ │ │ ├── cgmlp.py │ │ │ ├── encoder.py │ │ │ ├── fastformer.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── campplus │ │ │ ├── __init__.py │ │ │ ├── cluster_backend.py │ │ │ ├── components.py │ │ │ ├── model.py │ │ │ ├── template.yaml │ │ │ └── utils.py │ │ ├── conformer │ │ │ ├── __init__.py │ │ │ ├── encoder.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── contextual_paraformer │ │ │ ├── __init__.py │ │ │ ├── decoder.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── ct_transformer │ │ │ ├── __init__.py │ │ │ ├── model.py │ │ │ ├── template.yaml │ │ │ └── utils.py │ │ ├── ct_transformer_streaming │ │ │ ├── __init__.py │ │ │ ├── attention.py │ │ │ ├── encoder.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── ctc │ │ │ ├── __init__.py │ │ │ └── ctc.py │ │ ├── data2vec │ │ │ ├── __init__.py │ │ │ ├── data2vec.py │ │ │ ├── data2vec_encoder.py │ │ │ ├── data_utils.py │ │ │ ├── ema_module.py │ │ │ ├── grad_multiply.py │ │ │ ├── multihead_attention.py │ │ │ ├── quant_noise.py │ │ │ ├── utils.py │ │ │ └── wav2vec2.py │ │ ├── e_branchformer │ │ │ ├── __init__.py │ │ │ ├── encoder.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── eend │ │ │ ├── __init__.py │ │ │ ├── e2e_diar_eend_ola.py │ │ │ ├── eend_ola_dataloader.py │ │ │ ├── encoder.py │ │ │ ├── encoder_decoder_attractor.py │ │ │ └── utils │ │ │ │ ├── __init__.py │ │ │ │ ├── feature.py │ │ │ │ ├── kaldi_data.py │ │ │ │ ├── losses.py │ │ │ │ ├── power.py │ │ │ │ └── report.py │ │ ├── emotion2vec │ │ │ ├── __init__.py │ │ │ ├── audio.py │ │ │ ├── base.py │ │ │ ├── fairseq_modules.py │ │ │ ├── model.py │ │ │ ├── modules.py │ │ │ ├── template.yaml │ │ │ └── timm_modules.py │ │ ├── eres2net │ │ │ ├── __init__.py │ │ │ ├── eres2net.py │ │ │ ├── eres2net_aug.py │ │ │ └── fusion.py │ │ ├── fsmn_vad_streaming │ │ │ ├── __init__.py │ │ │ ├── encoder.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── language_model │ │ │ ├── __init__.py │ │ │ ├── rnn │ │ │ │ ├── __init__.py │ │ │ │ ├── argument.py │ │ │ │ ├── attentions.py │ │ │ │ ├── decoders.py │ │ │ │ └── encoders.py │ │ │ ├── seq_rnn_lm.py │ │ │ ├── transformer_encoder.py │ │ │ └── transformer_lm.py │ │ ├── lora │ │ │ ├── __init__.py │ │ │ ├── layers.py │ │ │ └── utils.py │ │ ├── mfcca │ │ │ ├── __init__.py │ │ │ ├── e2e_asr_mfcca.py │ │ │ ├── encoder_layer_mfcca.py │ │ │ └── mfcca_encoder.py │ │ ├── model_hf │ │ │ └── __init__.py │ │ ├── monotonic_aligner │ │ │ ├── __init__.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── mossformer │ │ │ ├── __init__.py │ │ │ ├── e2e_ss.py │ │ │ ├── mossformer.py │ │ │ ├── mossformer_decoder.py │ │ │ └── mossformer_encoder.py │ │ ├── normalize │ │ │ ├── __init__.py │ │ │ ├── global_mvn.py │ │ │ └── utterance_mvn.py │ │ ├── paraformer │ │ │ ├── __init__.py │ │ │ ├── cif_predictor.py │ │ │ ├── decoder.py │ │ │ ├── model.py │ │ │ ├── search.py │ │ │ └── template.yaml │ │ ├── paraformer_streaming │ │ │ ├── __init__.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── rwkv_bat │ │ │ ├── __init__.py │ │ │ ├── cuda_decoder │ │ │ │ ├── wkv_cuda.cu │ │ │ │ └── wkv_op.cpp │ │ │ ├── cuda_encoder │ │ │ │ ├── wkv_cuda.cu │ │ │ │ └── wkv_op.cpp │ │ │ ├── rwkv.py │ │ │ ├── rwkv_attention.py │ │ │ ├── rwkv_encoder.py │ │ │ ├── rwkv_feed_forward.py │ │ │ └── rwkv_subsampling.py │ │ ├── sa_asr │ │ │ ├── __init__.py │ │ │ ├── attention.py │ │ │ ├── beam_search_sa_asr.py │ │ │ ├── e2e_sa_asr.py │ │ │ └── transformer_decoder.py │ │ ├── sanm │ │ │ ├── __init__.py │ │ │ ├── attention.py │ │ │ ├── decoder.py │ │ │ ├── encoder.py │ │ │ ├── model.py │ │ │ ├── positionwise_feed_forward.py │ │ │ └── template.yaml │ │ ├── scama │ │ │ ├── __init__.py │ │ │ ├── beam_search.py │ │ │ ├── chunk_utilis.py │ │ │ ├── decoder.py │ │ │ ├── encoder.py │ │ │ ├── model.py │ │ │ ├── template.yaml │ │ │ └── utils.py │ │ ├── seaco_paraformer │ │ │ ├── __init__.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── sond │ │ │ ├── __init__.py │ │ │ ├── attention.py │ │ │ ├── e2e_diar_sond.py │ │ │ ├── encoder │ │ │ │ ├── __init__.py │ │ │ │ ├── ci_scorers.py │ │ │ │ ├── conv_encoder.py │ │ │ │ ├── ecapa_tdnn_encoder.py │ │ │ │ ├── fsmn_encoder.py │ │ │ │ ├── resnet34_encoder.py │ │ │ │ └── self_attention_encoder.py │ │ │ ├── label_aggregation.py │ │ │ ├── pooling │ │ │ │ ├── __init__.py │ │ │ │ ├── pooling_layers.py │ │ │ │ └── statistic_pooling.py │ │ │ └── sv_decoder.py │ │ ├── specaug │ │ │ ├── __init__.py │ │ │ ├── mask_along_axis.py │ │ │ ├── profileaug.py │ │ │ ├── specaug.py │ │ │ └── time_warp.py │ │ ├── transducer │ │ │ ├── __init__.py │ │ │ ├── beam_search_transducer.py │ │ │ ├── joint_network.py │ │ │ ├── model.py │ │ │ ├── rnn_decoder.py │ │ │ └── rnnt_decoder.py │ │ ├── transformer │ │ │ ├── __init__.py │ │ │ ├── attention.py │ │ │ ├── decoder.py │ │ │ ├── embedding.py │ │ │ ├── encoder.py │ │ │ ├── layer_norm.py │ │ │ ├── model.py │ │ │ ├── positionwise_feed_forward.py │ │ │ ├── scorers │ │ │ │ ├── __init__.py │ │ │ │ ├── ctc.py │ │ │ │ ├── ctc_prefix_score.py │ │ │ │ ├── length_bonus.py │ │ │ │ └── scorer_interface.py │ │ │ ├── search.py │ │ │ ├── template.yaml │ │ │ └── utils │ │ │ │ ├── __init__.py │ │ │ │ ├── add_sos_eos.py │ │ │ │ ├── dynamic_conv.py │ │ │ │ ├── dynamic_conv2d.py │ │ │ │ ├── lightconv.py │ │ │ │ ├── lightconv2d.py │ │ │ │ ├── mask.py │ │ │ │ ├── multi_layer_conv.py │ │ │ │ ├── nets_utils.py │ │ │ │ ├── repeat.py │ │ │ │ ├── subsampling.py │ │ │ │ ├── subsampling_without_posenc.py │ │ │ │ └── vgg2l.py │ │ ├── uniasr │ │ │ ├── __init__.py │ │ │ ├── beam_search.py │ │ │ ├── model.py │ │ │ └── template.yaml │ │ ├── whisper │ │ │ ├── __init__.py │ │ │ ├── model.py │ │ │ └── utils │ │ │ │ ├── __init__.py │ │ │ │ ├── assets │ │ │ │ ├── gpt2 │ │ │ │ │ ├── merges.txt │ │ │ │ │ ├── special_tokens_map.json │ │ │ │ │ ├── tokenizer_config.json │ │ │ │ │ └── vocab.json │ │ │ │ ├── mel_filters.npz │ │ │ │ └── multilingual │ │ │ │ │ ├── added_tokens.json │ │ │ │ │ ├── merges.txt │ │ │ │ │ ├── special_tokens_map.json │ │ │ │ │ ├── tokenizer_config.json │ │ │ │ │ └── vocab.json │ │ │ │ ├── audio.py │ │ │ │ ├── decoding.py │ │ │ │ ├── tokenizer.py │ │ │ │ ├── transcribe.py │ │ │ │ └── utils.py │ │ └── xvector │ │ │ ├── __init__.py │ │ │ └── e2e_sv.py │ ├── optimizers │ │ ├── __init__.py │ │ ├── fairseq_adam.py │ │ └── sgd.py │ ├── register.py │ ├── schedulers │ │ ├── __init__.py │ │ ├── abs_scheduler.py │ │ ├── noam_lr.py │ │ ├── tri_stage_scheduler.py │ │ └── warmup_lr.py │ ├── tokenizer │ │ ├── __init__.py │ │ ├── abs_tokenizer.py │ │ ├── build_tokenizer.py │ │ ├── char_tokenizer.py │ │ ├── cleaner.py │ │ ├── korean_cleaner.py │ │ ├── phoneme_tokenizer.py │ │ ├── sentencepiece_tokenizer.py │ │ ├── token_id_converter.py │ │ └── word_tokenizer.py │ ├── train_utils │ │ ├── __init__.py │ │ ├── add_gradient_noise.py │ │ ├── average_nbest_models.py │ │ ├── device_funcs.py │ │ ├── forward_adaptor.py │ │ ├── initialize.py │ │ ├── load_pretrained_model.py │ │ ├── model_summary.py │ │ ├── recursive_op.py │ │ ├── set_all_random_seed.py │ │ └── trainer.py │ ├── utils │ │ ├── __init__.py │ │ ├── datadir_writer.py │ │ ├── load_utils.py │ │ ├── misc.py │ │ ├── postprocess_utils.py │ │ ├── prepare_data.py │ │ ├── speaker_utils.py │ │ ├── timestamp_tools.py │ │ ├── types.py │ │ └── vad_utils.py │ └── version.txt ├── offline_inference.py ├── requirements.txt ├── speakers │ ├── TingtingRAP_prompt.wav │ ├── Tingting_prompt.wav │ ├── Tingting哼唱_prompt.wav │ └── speakers_info.json ├── stepaudio.py ├── tokenizer.py ├── tts.py ├── tts_inference.py └── utils.py ├── step_audio.py └── ultravox.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/README.md -------------------------------------------------------------------------------- /api_judge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/api_judge.py -------------------------------------------------------------------------------- /evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/evaluate.py -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/main.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/requirements.txt -------------------------------------------------------------------------------- /src/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/api/__init__.py: -------------------------------------------------------------------------------- 1 | from .gpt import generate_text_chat -------------------------------------------------------------------------------- /src/api/gpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/api/gpt.py -------------------------------------------------------------------------------- /src/evaluator/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/__init__.py -------------------------------------------------------------------------------- /src/evaluator/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/base.py -------------------------------------------------------------------------------- /src/evaluator/bbh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/bbh.py -------------------------------------------------------------------------------- /src/evaluator/harm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/harm.py -------------------------------------------------------------------------------- /src/evaluator/ifeval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/ifeval.py -------------------------------------------------------------------------------- /src/evaluator/instruction_following_eval/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/instruction_following_eval/README.md -------------------------------------------------------------------------------- /src/evaluator/instruction_following_eval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/evaluator/instruction_following_eval/instructions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/instruction_following_eval/instructions.py -------------------------------------------------------------------------------- /src/evaluator/instruction_following_eval/instructions_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/instruction_following_eval/instructions_registry.py -------------------------------------------------------------------------------- /src/evaluator/instruction_following_eval/instructions_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/instruction_following_eval/instructions_util.py -------------------------------------------------------------------------------- /src/evaluator/mcq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/mcq.py -------------------------------------------------------------------------------- /src/evaluator/open.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/open.py -------------------------------------------------------------------------------- /src/evaluator/qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/evaluator/qa.py -------------------------------------------------------------------------------- /src/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/__init__.py -------------------------------------------------------------------------------- /src/models/baichuan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/baichuan.py -------------------------------------------------------------------------------- /src/models/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/base.py -------------------------------------------------------------------------------- /src/models/diva.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/diva.py -------------------------------------------------------------------------------- /src/models/freeze_omni.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/freeze_omni.py -------------------------------------------------------------------------------- /src/models/glm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/glm.py -------------------------------------------------------------------------------- /src/models/gpt4o.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/gpt4o.py -------------------------------------------------------------------------------- /src/models/ichigo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/ichigo.py -------------------------------------------------------------------------------- /src/models/lyra.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/lyra.py -------------------------------------------------------------------------------- /src/models/megrez.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/megrez.py -------------------------------------------------------------------------------- /src/models/meralion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/meralion.py -------------------------------------------------------------------------------- /src/models/mini_omni.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/mini_omni.py -------------------------------------------------------------------------------- /src/models/mini_omni2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/mini_omni2.py -------------------------------------------------------------------------------- /src/models/minicpm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/minicpm.py -------------------------------------------------------------------------------- /src/models/moshi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/moshi.py -------------------------------------------------------------------------------- /src/models/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/naive.py -------------------------------------------------------------------------------- /src/models/naive2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/naive2.py -------------------------------------------------------------------------------- /src/models/naive3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/naive3.py -------------------------------------------------------------------------------- /src/models/naive4.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/naive4.py -------------------------------------------------------------------------------- /src/models/phi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/phi.py -------------------------------------------------------------------------------- /src/models/qwen2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/qwen2.py -------------------------------------------------------------------------------- /src/models/qwen_omni.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/qwen_omni.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_freeze_omni/adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/adapter.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/audioLLM.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/audioLLM.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/decoder/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/decoder/decoder.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/decoder/llm2tts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/decoder/llm2tts.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/decoder/ticodec/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/decoder/ticodec/models.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/decoder/ticodec/vqvae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/decoder/ticodec/vqvae.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/decoder/ticodec/vqvae_tester.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/decoder/ticodec/vqvae_tester.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/encoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_freeze_omni/encoder/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/encoder/attention.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/encoder/cmvn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/encoder/cmvn.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/encoder/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/encoder/encoder.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/encoder/subsampling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/encoder/subsampling.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/encoder/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/encoder/transformer.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/masks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/masks.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/pipeline.py -------------------------------------------------------------------------------- /src/models/src_freeze_omni/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_freeze_omni/utils.py -------------------------------------------------------------------------------- /src/models/src_glm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_glm/speech_tokenizer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_glm/speech_tokenizer/configuration_whisper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_glm/speech_tokenizer/configuration_whisper.py -------------------------------------------------------------------------------- /src/models/src_glm/speech_tokenizer/generation_whisper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_glm/speech_tokenizer/generation_whisper.py -------------------------------------------------------------------------------- /src/models/src_glm/speech_tokenizer/modeling_whisper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_glm/speech_tokenizer/modeling_whisper.py -------------------------------------------------------------------------------- /src/models/src_glm/speech_tokenizer/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_glm/speech_tokenizer/utils.py -------------------------------------------------------------------------------- /src/models/src_lyra/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_lyra/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/constants.py -------------------------------------------------------------------------------- /src/models/src_lyra/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/conversation.py -------------------------------------------------------------------------------- /src/models/src_lyra/mm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/mm_utils.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/__init__.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/builder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/language_model/lyra_qwen2vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/language_model/lyra_qwen2vl.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/language_model/lyra_qwen2vl_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/language_model/lyra_qwen2vl_extractor.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/language_model/lyra_qwen2vl_speechgenerator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/language_model/lyra_qwen2vl_speechgenerator.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/lyra_arch_qwen2vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/lyra_arch_qwen2vl.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/lyra_arch_qwen2vl_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/lyra_arch_qwen2vl_extractor.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/builder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/clip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/clip_encoder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/eva_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/eva_encoder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/imagebind/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/imagebind/data.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/imagebind/helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/imagebind/helpers.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/imagebind/imagebind_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/imagebind/imagebind_model.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/imagebind/multimodal_preprocessors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/imagebind/multimodal_preprocessors.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/imagebind/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/imagebind/transformer.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/imagebind_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/imagebind_encoder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/intern_vit_6b/configuration_intern_vit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/intern_vit_6b/configuration_intern_vit.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/intern_vit_6b/flash_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/intern_vit_6b/flash_attention.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/intern_vit_6b/modeling_intern_vit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/intern_vit_6b/modeling_intern_vit.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/openclip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/openclip_encoder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/qwen2vl_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/qwen2vl_encoder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/siglip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/siglip_encoder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_encoder/whisper_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_encoder/whisper_encoder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_generator/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_generator/builder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_generator/generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_generator/generation.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_generator/speech_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_generator/speech_generator.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/multimodal_projector/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/multimodal_projector/builder.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/qwen2vl_top_attn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/qwen2vl_top_attn.py -------------------------------------------------------------------------------- /src/models/src_lyra/model/soft_dtw_cuda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/model/soft_dtw_cuda.py -------------------------------------------------------------------------------- /src/models/src_lyra/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_lyra/utils.py -------------------------------------------------------------------------------- /src/models/src_mini_omni/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/LICENSE -------------------------------------------------------------------------------- /src/models/src_mini_omni/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/README.md -------------------------------------------------------------------------------- /src/models/src_mini_omni/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/__init__.py -------------------------------------------------------------------------------- /src/models/src_mini_omni/litgpt/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/litgpt/__init__.py -------------------------------------------------------------------------------- /src/models/src_mini_omni/litgpt/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/litgpt/config.py -------------------------------------------------------------------------------- /src/models/src_mini_omni/litgpt/generate/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_mini_omni/litgpt/generate/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/litgpt/generate/base.py -------------------------------------------------------------------------------- /src/models/src_mini_omni/litgpt/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/litgpt/model.py -------------------------------------------------------------------------------- /src/models/src_mini_omni/litgpt/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/litgpt/tokenizer.py -------------------------------------------------------------------------------- /src/models/src_mini_omni/litgpt/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/litgpt/utils.py -------------------------------------------------------------------------------- /src/models/src_mini_omni/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/requirements.txt -------------------------------------------------------------------------------- /src/models/src_mini_omni/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_mini_omni/utils/assets/silero_vad.onnx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/utils/assets/silero_vad.onnx -------------------------------------------------------------------------------- /src/models/src_mini_omni/utils/snac_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/utils/snac_utils.py -------------------------------------------------------------------------------- /src/models/src_mini_omni/utils/vad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni/utils/vad.py -------------------------------------------------------------------------------- /src/models/src_mini_omni2/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/LICENSE -------------------------------------------------------------------------------- /src/models/src_mini_omni2/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/README.md -------------------------------------------------------------------------------- /src/models/src_mini_omni2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/__init__.py -------------------------------------------------------------------------------- /src/models/src_mini_omni2/inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/inference.py -------------------------------------------------------------------------------- /src/models/src_mini_omni2/litgpt/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/litgpt/__init__.py -------------------------------------------------------------------------------- /src/models/src_mini_omni2/litgpt/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/litgpt/config.py -------------------------------------------------------------------------------- /src/models/src_mini_omni2/litgpt/generate/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_mini_omni2/litgpt/generate/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/litgpt/generate/base.py -------------------------------------------------------------------------------- /src/models/src_mini_omni2/litgpt/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/litgpt/model.py -------------------------------------------------------------------------------- /src/models/src_mini_omni2/litgpt/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/litgpt/tokenizer.py -------------------------------------------------------------------------------- /src/models/src_mini_omni2/litgpt/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/litgpt/utils.py -------------------------------------------------------------------------------- /src/models/src_mini_omni2/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_mini_omni2/utils/assets/silero_vad.onnx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/utils/assets/silero_vad.onnx -------------------------------------------------------------------------------- /src/models/src_mini_omni2/utils/snac_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/utils/snac_utils.py -------------------------------------------------------------------------------- /src/models/src_mini_omni2/utils/vad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_mini_omni2/utils/vad.py -------------------------------------------------------------------------------- /src/models/src_step_audio/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/LICENSE -------------------------------------------------------------------------------- /src/models/src_step_audio/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/README.md -------------------------------------------------------------------------------- /src/models/src_step_audio/README_CN.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/README_CN.md -------------------------------------------------------------------------------- /src/models/src_step_audio/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/app.py -------------------------------------------------------------------------------- /src/models/src_step_audio/assets/Step-Audio.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/assets/Step-Audio.pdf -------------------------------------------------------------------------------- /src/models/src_step_audio/assets/architecture.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/assets/architecture.png -------------------------------------------------------------------------------- /src/models/src_step_audio/assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/assets/logo.png -------------------------------------------------------------------------------- /src/models/src_step_audio/assets/pipeline.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/assets/pipeline.png -------------------------------------------------------------------------------- /src/models/src_step_audio/assets/rlhf.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/assets/rlhf.png -------------------------------------------------------------------------------- /src/models/src_step_audio/assets/stepeval_radar_chart.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/assets/stepeval_radar_chart.png -------------------------------------------------------------------------------- /src/models/src_step_audio/assets/yuewen.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/assets/yuewen.jpeg -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/cli/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/cli/cosyvoice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/cli/cosyvoice.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/cli/frontend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/cli/frontend.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/cli/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/cli/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/flow/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/flow/decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/flow/flow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/flow/flow.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/flow/flow_matching.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/flow/flow_matching.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/flow/length_regulator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/flow/length_regulator.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/hifigan/f0_predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/hifigan/f0_predictor.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/hifigan/generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/hifigan/generator.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/matcha/audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/matcha/audio.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/matcha/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/matcha/decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/matcha/flow_matching.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/matcha/flow_matching.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/matcha/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/matcha/transformer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/activation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/activation.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/attention.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/convolution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/convolution.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/decoder_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/decoder_layer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/embedding.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/encoder_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/encoder_layer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/label_smoothing_loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/label_smoothing_loss.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/positionwise_feed_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/positionwise_feed_forward.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/transformer/subsampling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/transformer/subsampling.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/utils/audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/utils/audio.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/utils/class_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/utils/class_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/utils/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/utils/common.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/utils/executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/utils/executor.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/utils/file_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/utils/file_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/utils/frontend_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/utils/frontend_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/utils/mask.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/utils/mask.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/utils/scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/utils/scheduler.py -------------------------------------------------------------------------------- /src/models/src_step_audio/cosyvoice/utils/train_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/cosyvoice/utils/train_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/__init__.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/auto/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/auto/auto_frontend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/auto/auto_frontend.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/auto/auto_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/auto/auto_model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/auto/auto_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/auto/auto_tokenizer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/bin/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/bin/compute_audio_cmvn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/bin/compute_audio_cmvn.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/bin/inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/bin/inference.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/bin/tokenize_text.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/bin/tokenize_text.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/bin/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/bin/train.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/datasets/audio_datasets/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/datasets/audio_datasets/datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/datasets/audio_datasets/datasets.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/datasets/audio_datasets/index_ds.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/datasets/audio_datasets/index_ds.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/datasets/audio_datasets/preprocessor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/datasets/audio_datasets/preprocessor.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/datasets/audio_datasets/samplers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/datasets/audio_datasets/samplers.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/datasets/audio_datasets/scp2jsonl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/datasets/audio_datasets/scp2jsonl.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/download/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/download/download_dataset_from_hub.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/download/download_dataset_from_hub.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/download/download_from_hub.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/download/download_from_hub.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/download/file.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/download/file.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/download/name_maps_from_hub.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/download/name_maps_from_hub.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/download/runtime_sdk_download_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/download/runtime_sdk_download_tool.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/default.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/default.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/eend_ola_feature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/eend_ola_feature.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/fused.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/fused.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/s3prl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/s3prl.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/utils/__init__.py: -------------------------------------------------------------------------------- 1 | """Initialize sub package.""" 2 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/utils/beamformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/utils/beamformer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/utils/complex_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/utils/complex_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/utils/dnn_beamformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/utils/dnn_beamformer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/utils/dnn_wpe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/utils/dnn_wpe.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/utils/feature_transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/utils/feature_transform.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/utils/frontend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/utils/frontend.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/utils/log_mel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/utils/log_mel.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/utils/mask_estimator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/utils/mask_estimator.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/utils/stft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/utils/stft.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/wav_frontend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/wav_frontend.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/frontends/windowing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/frontends/windowing.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/losses/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/losses/label_smoothing_loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/losses/label_smoothing_loss.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/metrics/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/metrics/common.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/metrics/compute_acc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/metrics/compute_acc.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/metrics/compute_eer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/metrics/compute_eer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/metrics/compute_min_dcf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/metrics/compute_min_dcf.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/metrics/compute_wer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/metrics/compute_wer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/bat/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/bat/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/bat/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/bicif_paraformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/bicif_paraformer/cif_predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/bicif_paraformer/cif_predictor.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/bicif_paraformer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/bicif_paraformer/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/bicif_paraformer/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/bicif_paraformer/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/branchformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/branchformer/cgmlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/branchformer/cgmlp.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/branchformer/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/branchformer/encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/branchformer/fastformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/branchformer/fastformer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/branchformer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/branchformer/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/branchformer/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/branchformer/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/campplus/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/campplus/cluster_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/campplus/cluster_backend.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/campplus/components.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/campplus/components.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/campplus/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/campplus/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/campplus/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/campplus/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/campplus/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/campplus/utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/conformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/conformer/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/conformer/encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/conformer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/conformer/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/conformer/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/conformer/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/contextual_paraformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/contextual_paraformer/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/contextual_paraformer/decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/contextual_paraformer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/contextual_paraformer/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/contextual_paraformer/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/contextual_paraformer/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ct_transformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ct_transformer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/ct_transformer/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ct_transformer/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/ct_transformer/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ct_transformer/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/ct_transformer/utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ct_transformer_streaming/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ct_transformer_streaming/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/ct_transformer_streaming/attention.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ct_transformer_streaming/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/ct_transformer_streaming/encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ct_transformer_streaming/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/ct_transformer_streaming/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ct_transformer_streaming/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/ct_transformer_streaming/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ctc/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/ctc/ctc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/ctc/ctc.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/data2vec/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/data2vec/data2vec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/data2vec/data2vec.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/data2vec/data2vec_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/data2vec/data2vec_encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/data2vec/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/data2vec/data_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/data2vec/ema_module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/data2vec/ema_module.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/data2vec/grad_multiply.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/data2vec/grad_multiply.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/data2vec/multihead_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/data2vec/multihead_attention.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/data2vec/quant_noise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/data2vec/quant_noise.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/data2vec/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/data2vec/utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/data2vec/wav2vec2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/data2vec/wav2vec2.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/e_branchformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/e_branchformer/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/e_branchformer/encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/e_branchformer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/e_branchformer/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/e_branchformer/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/e_branchformer/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/e2e_diar_eend_ola.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eend/e2e_diar_eend_ola.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/eend_ola_dataloader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eend/eend_ola_dataloader.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eend/encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/encoder_decoder_attractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eend/encoder_decoder_attractor.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/utils/feature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eend/utils/feature.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/utils/kaldi_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eend/utils/kaldi_data.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/utils/losses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eend/utils/losses.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/utils/power.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eend/utils/power.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eend/utils/report.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eend/utils/report.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/emotion2vec/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/emotion2vec/audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/emotion2vec/audio.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/emotion2vec/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/emotion2vec/base.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/emotion2vec/fairseq_modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/emotion2vec/fairseq_modules.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/emotion2vec/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/emotion2vec/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/emotion2vec/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/emotion2vec/modules.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/emotion2vec/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/emotion2vec/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/emotion2vec/timm_modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/emotion2vec/timm_modules.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eres2net/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eres2net/__init__.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eres2net/eres2net.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eres2net/eres2net.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eres2net/eres2net_aug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eres2net/eres2net_aug.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/eres2net/fusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/eres2net/fusion.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/fsmn_vad_streaming/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/fsmn_vad_streaming/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/fsmn_vad_streaming/encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/fsmn_vad_streaming/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/fsmn_vad_streaming/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/fsmn_vad_streaming/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/fsmn_vad_streaming/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/language_model/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/language_model/rnn/__init__.py: -------------------------------------------------------------------------------- 1 | """Initialize sub package.""" 2 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/language_model/rnn/argument.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/language_model/rnn/argument.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/language_model/rnn/attentions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/language_model/rnn/attentions.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/language_model/rnn/decoders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/language_model/rnn/decoders.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/language_model/rnn/encoders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/language_model/rnn/encoders.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/language_model/seq_rnn_lm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/language_model/seq_rnn_lm.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/language_model/transformer_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/language_model/transformer_encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/language_model/transformer_lm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/language_model/transformer_lm.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/lora/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/lora/layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/lora/layers.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/lora/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/lora/utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/mfcca/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/mfcca/e2e_asr_mfcca.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/mfcca/e2e_asr_mfcca.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/mfcca/encoder_layer_mfcca.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/mfcca/encoder_layer_mfcca.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/mfcca/mfcca_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/mfcca/mfcca_encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/model_hf/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/monotonic_aligner/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/monotonic_aligner/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/monotonic_aligner/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/monotonic_aligner/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/monotonic_aligner/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/mossformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/mossformer/e2e_ss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/mossformer/e2e_ss.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/mossformer/mossformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/mossformer/mossformer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/mossformer/mossformer_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/mossformer/mossformer_decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/mossformer/mossformer_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/mossformer/mossformer_encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/normalize/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/normalize/global_mvn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/normalize/global_mvn.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/normalize/utterance_mvn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/normalize/utterance_mvn.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/paraformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/paraformer/cif_predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/paraformer/cif_predictor.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/paraformer/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/paraformer/decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/paraformer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/paraformer/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/paraformer/search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/paraformer/search.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/paraformer/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/paraformer/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/paraformer_streaming/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/paraformer_streaming/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/paraformer_streaming/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/paraformer_streaming/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/paraformer_streaming/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/rwkv_bat/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/rwkv_bat/cuda_decoder/wkv_cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/rwkv_bat/cuda_decoder/wkv_cuda.cu -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/rwkv_bat/cuda_decoder/wkv_op.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/rwkv_bat/cuda_decoder/wkv_op.cpp -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/rwkv_bat/cuda_encoder/wkv_cuda.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/rwkv_bat/cuda_encoder/wkv_cuda.cu -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/rwkv_bat/cuda_encoder/wkv_op.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/rwkv_bat/cuda_encoder/wkv_op.cpp -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/rwkv_bat/rwkv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/rwkv_bat/rwkv.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/rwkv_bat/rwkv_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/rwkv_bat/rwkv_attention.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/rwkv_bat/rwkv_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/rwkv_bat/rwkv_encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/rwkv_bat/rwkv_feed_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/rwkv_bat/rwkv_feed_forward.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/rwkv_bat/rwkv_subsampling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/rwkv_bat/rwkv_subsampling.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sa_asr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sa_asr/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sa_asr/attention.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sa_asr/beam_search_sa_asr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sa_asr/beam_search_sa_asr.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sa_asr/e2e_sa_asr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sa_asr/e2e_sa_asr.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sa_asr/transformer_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sa_asr/transformer_decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sanm/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sanm/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sanm/attention.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sanm/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sanm/decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sanm/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sanm/encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sanm/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sanm/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sanm/positionwise_feed_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sanm/positionwise_feed_forward.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sanm/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sanm/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/scama/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/scama/beam_search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/scama/beam_search.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/scama/chunk_utilis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/scama/chunk_utilis.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/scama/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/scama/decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/scama/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/scama/encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/scama/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/scama/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/scama/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/scama/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/scama/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/scama/utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/seaco_paraformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/seaco_paraformer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/seaco_paraformer/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/seaco_paraformer/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/seaco_paraformer/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/attention.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/e2e_diar_sond.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/e2e_diar_sond.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/encoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/encoder/ci_scorers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/encoder/ci_scorers.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/encoder/conv_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/encoder/conv_encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/encoder/ecapa_tdnn_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/encoder/ecapa_tdnn_encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/encoder/fsmn_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/encoder/fsmn_encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/encoder/resnet34_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/encoder/resnet34_encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/encoder/self_attention_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/encoder/self_attention_encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/label_aggregation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/label_aggregation.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/pooling/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/pooling/pooling_layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/pooling/pooling_layers.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/pooling/statistic_pooling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/pooling/statistic_pooling.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/sond/sv_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/sond/sv_decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/specaug/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/specaug/mask_along_axis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/specaug/mask_along_axis.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/specaug/profileaug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/specaug/profileaug.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/specaug/specaug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/specaug/specaug.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/specaug/time_warp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/specaug/time_warp.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transducer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transducer/beam_search_transducer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transducer/beam_search_transducer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transducer/joint_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transducer/joint_network.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transducer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transducer/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transducer/rnn_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transducer/rnn_decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transducer/rnnt_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transducer/rnnt_decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/attention.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/decoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/embedding.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/encoder.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/layer_norm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/layer_norm.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/positionwise_feed_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/positionwise_feed_forward.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/scorers/__init__.py: -------------------------------------------------------------------------------- 1 | """Initialize sub package.""" 2 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/scorers/ctc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/scorers/ctc.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/scorers/ctc_prefix_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/scorers/ctc_prefix_score.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/scorers/length_bonus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/scorers/length_bonus.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/scorers/scorer_interface.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/scorers/scorer_interface.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/search.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/add_sos_eos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/add_sos_eos.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/dynamic_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/dynamic_conv.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/dynamic_conv2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/dynamic_conv2d.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/lightconv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/lightconv.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/lightconv2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/lightconv2d.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/mask.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/mask.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/multi_layer_conv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/multi_layer_conv.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/nets_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/nets_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/repeat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/repeat.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/subsampling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/subsampling.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/subsampling_without_posenc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/subsampling_without_posenc.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/transformer/utils/vgg2l.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/transformer/utils/vgg2l.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/uniasr/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/uniasr/beam_search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/uniasr/beam_search.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/uniasr/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/uniasr/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/uniasr/template.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/uniasr/template.yaml -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/gpt2/merges.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/gpt2/merges.txt -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/gpt2/special_tokens_map.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/gpt2/special_tokens_map.json -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/gpt2/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/gpt2/tokenizer_config.json -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/gpt2/vocab.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/gpt2/vocab.json -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/mel_filters.npz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/mel_filters.npz -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/multilingual/added_tokens.json: -------------------------------------------------------------------------------- 1 | {"<|endoftext|>": 50257} 2 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/multilingual/merges.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/multilingual/merges.txt -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/multilingual/special_tokens_map.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/multilingual/special_tokens_map.json -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/multilingual/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/multilingual/tokenizer_config.json -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/multilingual/vocab.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/assets/multilingual/vocab.json -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/audio.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/decoding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/decoding.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/tokenizer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/transcribe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/transcribe.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/whisper/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/whisper/utils/utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/xvector/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/models/xvector/e2e_sv.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/models/xvector/e2e_sv.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/optimizers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/optimizers/__init__.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/optimizers/fairseq_adam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/optimizers/fairseq_adam.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/optimizers/sgd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/optimizers/sgd.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/register.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/register.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/schedulers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/schedulers/__init__.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/schedulers/abs_scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/schedulers/abs_scheduler.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/schedulers/noam_lr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/schedulers/noam_lr.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/schedulers/tri_stage_scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/schedulers/tri_stage_scheduler.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/schedulers/warmup_lr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/schedulers/warmup_lr.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/tokenizer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/tokenizer/abs_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/tokenizer/abs_tokenizer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/tokenizer/build_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/tokenizer/build_tokenizer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/tokenizer/char_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/tokenizer/char_tokenizer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/tokenizer/cleaner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/tokenizer/cleaner.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/tokenizer/korean_cleaner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/tokenizer/korean_cleaner.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/tokenizer/phoneme_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/tokenizer/phoneme_tokenizer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/tokenizer/sentencepiece_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/tokenizer/sentencepiece_tokenizer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/tokenizer/token_id_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/tokenizer/token_id_converter.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/tokenizer/word_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/tokenizer/word_tokenizer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/add_gradient_noise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/train_utils/add_gradient_noise.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/average_nbest_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/train_utils/average_nbest_models.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/device_funcs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/train_utils/device_funcs.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/forward_adaptor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/train_utils/forward_adaptor.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/initialize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/train_utils/initialize.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/load_pretrained_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/train_utils/load_pretrained_model.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/model_summary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/train_utils/model_summary.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/recursive_op.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/train_utils/recursive_op.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/set_all_random_seed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/train_utils/set_all_random_seed.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/train_utils/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/train_utils/trainer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/utils/datadir_writer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/utils/datadir_writer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/utils/load_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/utils/load_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/utils/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/utils/misc.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/utils/postprocess_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/utils/postprocess_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/utils/prepare_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/utils/prepare_data.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/utils/speaker_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/utils/speaker_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/utils/timestamp_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/utils/timestamp_tools.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/utils/types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/utils/types.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/utils/vad_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/funasr_detach/utils/vad_utils.py -------------------------------------------------------------------------------- /src/models/src_step_audio/funasr_detach/version.txt: -------------------------------------------------------------------------------- 1 | 1.0.8 2 | -------------------------------------------------------------------------------- /src/models/src_step_audio/offline_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/offline_inference.py -------------------------------------------------------------------------------- /src/models/src_step_audio/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/requirements.txt -------------------------------------------------------------------------------- /src/models/src_step_audio/speakers/TingtingRAP_prompt.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/speakers/TingtingRAP_prompt.wav -------------------------------------------------------------------------------- /src/models/src_step_audio/speakers/Tingting_prompt.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/speakers/Tingting_prompt.wav -------------------------------------------------------------------------------- /src/models/src_step_audio/speakers/Tingting哼唱_prompt.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/speakers/Tingting哼唱_prompt.wav -------------------------------------------------------------------------------- /src/models/src_step_audio/speakers/speakers_info.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/speakers/speakers_info.json -------------------------------------------------------------------------------- /src/models/src_step_audio/stepaudio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/stepaudio.py -------------------------------------------------------------------------------- /src/models/src_step_audio/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/tokenizer.py -------------------------------------------------------------------------------- /src/models/src_step_audio/tts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/tts.py -------------------------------------------------------------------------------- /src/models/src_step_audio/tts_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/tts_inference.py -------------------------------------------------------------------------------- /src/models/src_step_audio/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/src_step_audio/utils.py -------------------------------------------------------------------------------- /src/models/step_audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/step_audio.py -------------------------------------------------------------------------------- /src/models/ultravox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/MatthewCYM/VoiceBench/HEAD/src/models/ultravox.py --------------------------------------------------------------------------------