├── LICENSE ├── README.md ├── data ├── Emilia_ZH_EN_pinyin │ └── vocab.txt └── librispeech_pc_test_clean_cross_sentence.lst ├── requirements.txt └── src ├── ctcmodel.py ├── demo.ipynb ├── discriminator_conformer.py ├── dmd_trainer.py ├── duration_predictor.py ├── duration_trainer.py ├── duration_trainer_with_prompt.py ├── ecapa_tdnn.py ├── f5_tts ├── api.py ├── configs │ ├── E2TTS_Base.yaml │ ├── E2TTS_Small.yaml │ ├── F5TTS_Base.yaml │ ├── F5TTS_Small.yaml │ └── F5TTS_v1_Base.yaml ├── eval │ ├── README.md │ ├── ecapa_tdnn.py │ ├── eval_infer_batch.py │ ├── eval_infer_batch.sh │ ├── eval_librispeech_test_clean.py │ ├── eval_seedtts_testset.py │ ├── eval_utmos.py │ └── utils_eval.py ├── infer │ ├── README.md │ ├── SHARED.md │ ├── __pycache__ │ │ └── utils_infer.cpython-310.pyc │ ├── examples │ │ ├── basic │ │ │ ├── basic.toml │ │ │ ├── basic_ref_en.wav │ │ │ └── basic_ref_zh.wav │ │ ├── multi │ │ │ ├── country.flac │ │ │ ├── main.flac │ │ │ ├── story.toml │ │ │ ├── story.txt │ │ │ └── town.flac │ │ └── vocab.txt │ ├── infer_cli.py │ ├── infer_gradio.py │ ├── speech_edit.py │ └── utils_infer.py ├── model │ ├── __init__.py │ ├── backbones │ │ ├── README.md │ │ ├── __pycache__ │ │ │ ├── dit.cpython-310.pyc │ │ │ ├── mmdit.cpython-310.pyc │ │ │ └── unett.cpython-310.pyc │ │ ├── dit.py │ │ ├── mmdit.py │ │ └── unett.py │ ├── cfm.py │ ├── dataset.py │ ├── modules.py │ ├── trainer.py │ └── utils.py ├── model_new │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-310.pyc │ │ ├── cfm.cpython-310.pyc │ │ ├── modules.cpython-310.pyc │ │ ├── trainer.cpython-310.pyc │ │ └── utils.cpython-310.pyc │ ├── backbones │ │ ├── README.md │ │ ├── __pycache__ │ │ │ ├── dit.cpython-310.pyc │ │ │ ├── mmdit.cpython-310.pyc │ │ │ └── unett.cpython-310.pyc │ │ ├── dit.py │ │ ├── mmdit.py │ │ └── unett.py │ ├── cfm.py │ ├── dataset.py │ ├── modules.py │ ├── trainer.py │ └── utils.py ├── runtime │ └── triton_trtllm │ │ ├── Dockerfile.server │ │ ├── README.md │ │ ├── benchmark.py │ │ ├── client_grpc.py │ │ ├── client_http.py │ │ ├── docker-compose.yml │ │ ├── model_repo_f5_tts │ │ ├── f5_tts │ │ │ ├── 1 │ │ │ │ ├── f5_tts_trtllm.py │ │ │ │ └── model.py │ │ │ └── config.pbtxt │ │ └── vocoder │ │ │ ├── 1 │ │ │ └── .gitkeep │ │ │ └── config.pbtxt │ │ ├── patch │ │ ├── __init__.py │ │ └── f5tts │ │ │ ├── model.py │ │ │ └── modules.py │ │ ├── requirements-pytorch.txt │ │ ├── run.sh │ │ └── scripts │ │ ├── conv_stft.py │ │ ├── convert_checkpoint.py │ │ ├── export_vocoder_to_onnx.py │ │ ├── export_vocos_trt.sh │ │ └── fill_template.py ├── scripts │ ├── count_max_epoch.py │ └── count_params_gflops.py ├── socket_client.py ├── socket_server.py └── train │ ├── README.md │ ├── datasets │ ├── prepare_csv_wavs.py │ ├── prepare_emilia.py │ ├── prepare_emilia_v2.py │ ├── prepare_libritts.py │ ├── prepare_ljspeech.py │ └── prepare_wenetspeech4tts.py │ ├── finetune_cli.py │ ├── finetune_gradio.py │ └── train.py ├── grpo_duration_trainer.py ├── guidance_model.py ├── infer.py └── unimodel.py /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/README.md -------------------------------------------------------------------------------- /data/Emilia_ZH_EN_pinyin/vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/data/Emilia_ZH_EN_pinyin/vocab.txt -------------------------------------------------------------------------------- /data/librispeech_pc_test_clean_cross_sentence.lst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/data/librispeech_pc_test_clean_cross_sentence.lst -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/requirements.txt -------------------------------------------------------------------------------- /src/ctcmodel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/ctcmodel.py -------------------------------------------------------------------------------- /src/demo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/demo.ipynb -------------------------------------------------------------------------------- /src/discriminator_conformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/discriminator_conformer.py -------------------------------------------------------------------------------- /src/dmd_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/dmd_trainer.py -------------------------------------------------------------------------------- /src/duration_predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/duration_predictor.py -------------------------------------------------------------------------------- /src/duration_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/duration_trainer.py -------------------------------------------------------------------------------- /src/duration_trainer_with_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/duration_trainer_with_prompt.py -------------------------------------------------------------------------------- /src/ecapa_tdnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/ecapa_tdnn.py -------------------------------------------------------------------------------- /src/f5_tts/api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/api.py -------------------------------------------------------------------------------- /src/f5_tts/configs/E2TTS_Base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/configs/E2TTS_Base.yaml -------------------------------------------------------------------------------- /src/f5_tts/configs/E2TTS_Small.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/configs/E2TTS_Small.yaml -------------------------------------------------------------------------------- /src/f5_tts/configs/F5TTS_Base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/configs/F5TTS_Base.yaml -------------------------------------------------------------------------------- /src/f5_tts/configs/F5TTS_Small.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/configs/F5TTS_Small.yaml -------------------------------------------------------------------------------- /src/f5_tts/configs/F5TTS_v1_Base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/configs/F5TTS_v1_Base.yaml -------------------------------------------------------------------------------- /src/f5_tts/eval/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/eval/README.md -------------------------------------------------------------------------------- /src/f5_tts/eval/ecapa_tdnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/eval/ecapa_tdnn.py -------------------------------------------------------------------------------- /src/f5_tts/eval/eval_infer_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/eval/eval_infer_batch.py -------------------------------------------------------------------------------- /src/f5_tts/eval/eval_infer_batch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/eval/eval_infer_batch.sh -------------------------------------------------------------------------------- /src/f5_tts/eval/eval_librispeech_test_clean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/eval/eval_librispeech_test_clean.py -------------------------------------------------------------------------------- /src/f5_tts/eval/eval_seedtts_testset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/eval/eval_seedtts_testset.py -------------------------------------------------------------------------------- /src/f5_tts/eval/eval_utmos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/eval/eval_utmos.py -------------------------------------------------------------------------------- /src/f5_tts/eval/utils_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/eval/utils_eval.py -------------------------------------------------------------------------------- /src/f5_tts/infer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/README.md -------------------------------------------------------------------------------- /src/f5_tts/infer/SHARED.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/SHARED.md -------------------------------------------------------------------------------- /src/f5_tts/infer/__pycache__/utils_infer.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/__pycache__/utils_infer.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/basic/basic.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/examples/basic/basic.toml -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/basic/basic_ref_en.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/examples/basic/basic_ref_en.wav -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/basic/basic_ref_zh.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/examples/basic/basic_ref_zh.wav -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/multi/country.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/examples/multi/country.flac -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/multi/main.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/examples/multi/main.flac -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/multi/story.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/examples/multi/story.toml -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/multi/story.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/examples/multi/story.txt -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/multi/town.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/examples/multi/town.flac -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/examples/vocab.txt -------------------------------------------------------------------------------- /src/f5_tts/infer/infer_cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/infer_cli.py -------------------------------------------------------------------------------- /src/f5_tts/infer/infer_gradio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/infer_gradio.py -------------------------------------------------------------------------------- /src/f5_tts/infer/speech_edit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/speech_edit.py -------------------------------------------------------------------------------- /src/f5_tts/infer/utils_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/infer/utils_infer.py -------------------------------------------------------------------------------- /src/f5_tts/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/__init__.py -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/backbones/README.md -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/__pycache__/dit.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/backbones/__pycache__/dit.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/__pycache__/mmdit.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/backbones/__pycache__/mmdit.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/__pycache__/unett.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/backbones/__pycache__/unett.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/dit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/backbones/dit.py -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/mmdit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/backbones/mmdit.py -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/unett.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/backbones/unett.py -------------------------------------------------------------------------------- /src/f5_tts/model/cfm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/cfm.py -------------------------------------------------------------------------------- /src/f5_tts/model/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/dataset.py -------------------------------------------------------------------------------- /src/f5_tts/model/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/modules.py -------------------------------------------------------------------------------- /src/f5_tts/model/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/trainer.py -------------------------------------------------------------------------------- /src/f5_tts/model/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model/utils.py -------------------------------------------------------------------------------- /src/f5_tts/model_new/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/__init__.py -------------------------------------------------------------------------------- /src/f5_tts/model_new/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model_new/__pycache__/cfm.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/__pycache__/cfm.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model_new/__pycache__/modules.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/__pycache__/modules.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model_new/__pycache__/trainer.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/__pycache__/trainer.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model_new/__pycache__/utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/__pycache__/utils.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model_new/backbones/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/backbones/README.md -------------------------------------------------------------------------------- /src/f5_tts/model_new/backbones/__pycache__/dit.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/backbones/__pycache__/dit.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model_new/backbones/__pycache__/mmdit.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/backbones/__pycache__/mmdit.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model_new/backbones/__pycache__/unett.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/backbones/__pycache__/unett.cpython-310.pyc -------------------------------------------------------------------------------- /src/f5_tts/model_new/backbones/dit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/backbones/dit.py -------------------------------------------------------------------------------- /src/f5_tts/model_new/backbones/mmdit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/backbones/mmdit.py -------------------------------------------------------------------------------- /src/f5_tts/model_new/backbones/unett.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/backbones/unett.py -------------------------------------------------------------------------------- /src/f5_tts/model_new/cfm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/cfm.py -------------------------------------------------------------------------------- /src/f5_tts/model_new/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/dataset.py -------------------------------------------------------------------------------- /src/f5_tts/model_new/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/modules.py -------------------------------------------------------------------------------- /src/f5_tts/model_new/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/trainer.py -------------------------------------------------------------------------------- /src/f5_tts/model_new/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/model_new/utils.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/Dockerfile.server: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/Dockerfile.server -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/README.md -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/benchmark.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/benchmark.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/client_grpc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/client_grpc.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/client_http.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/client_http.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/docker-compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/docker-compose.yml -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/model_repo_f5_tts/f5_tts/1/f5_tts_trtllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/model_repo_f5_tts/f5_tts/1/f5_tts_trtllm.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/model_repo_f5_tts/f5_tts/1/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/model_repo_f5_tts/f5_tts/1/model.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/model_repo_f5_tts/f5_tts/config.pbtxt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/model_repo_f5_tts/f5_tts/config.pbtxt -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/model_repo_f5_tts/vocoder/1/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/model_repo_f5_tts/vocoder/config.pbtxt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/model_repo_f5_tts/vocoder/config.pbtxt -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/patch/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/patch/__init__.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/patch/f5tts/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/patch/f5tts/model.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/patch/f5tts/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/patch/f5tts/modules.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/requirements-pytorch.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/requirements-pytorch.txt -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/run.sh -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/scripts/conv_stft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/scripts/conv_stft.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/scripts/convert_checkpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/scripts/convert_checkpoint.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/scripts/export_vocoder_to_onnx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/scripts/export_vocoder_to_onnx.py -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/scripts/export_vocos_trt.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/scripts/export_vocos_trt.sh -------------------------------------------------------------------------------- /src/f5_tts/runtime/triton_trtllm/scripts/fill_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/runtime/triton_trtllm/scripts/fill_template.py -------------------------------------------------------------------------------- /src/f5_tts/scripts/count_max_epoch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/scripts/count_max_epoch.py -------------------------------------------------------------------------------- /src/f5_tts/scripts/count_params_gflops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/scripts/count_params_gflops.py -------------------------------------------------------------------------------- /src/f5_tts/socket_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/socket_client.py -------------------------------------------------------------------------------- /src/f5_tts/socket_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/socket_server.py -------------------------------------------------------------------------------- /src/f5_tts/train/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/train/README.md -------------------------------------------------------------------------------- /src/f5_tts/train/datasets/prepare_csv_wavs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/train/datasets/prepare_csv_wavs.py -------------------------------------------------------------------------------- /src/f5_tts/train/datasets/prepare_emilia.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/train/datasets/prepare_emilia.py -------------------------------------------------------------------------------- /src/f5_tts/train/datasets/prepare_emilia_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/train/datasets/prepare_emilia_v2.py -------------------------------------------------------------------------------- /src/f5_tts/train/datasets/prepare_libritts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/train/datasets/prepare_libritts.py -------------------------------------------------------------------------------- /src/f5_tts/train/datasets/prepare_ljspeech.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/train/datasets/prepare_ljspeech.py -------------------------------------------------------------------------------- /src/f5_tts/train/datasets/prepare_wenetspeech4tts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/train/datasets/prepare_wenetspeech4tts.py -------------------------------------------------------------------------------- /src/f5_tts/train/finetune_cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/train/finetune_cli.py -------------------------------------------------------------------------------- /src/f5_tts/train/finetune_gradio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/train/finetune_gradio.py -------------------------------------------------------------------------------- /src/f5_tts/train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/f5_tts/train/train.py -------------------------------------------------------------------------------- /src/grpo_duration_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/grpo_duration_trainer.py -------------------------------------------------------------------------------- /src/guidance_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/guidance_model.py -------------------------------------------------------------------------------- /src/infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/infer.py -------------------------------------------------------------------------------- /src/unimodel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yl4579/DMOSpeech2/HEAD/src/unimodel.py --------------------------------------------------------------------------------