├── .github └── workflows │ ├── pre-commit.yaml │ ├── publish-docker-image.yaml │ └── sync-hf.yaml ├── .gitignore ├── .gitmodules ├── .pre-commit-config.yaml ├── Dockerfile ├── LICENSE ├── MANIFEST.in ├── README.md ├── ckpts └── README.md ├── data ├── Emilia_ZH_EN_pinyin │ └── vocab.txt └── librispeech_pc_test_clean_cross_sentence.lst ├── pyproject.toml ├── ruff.toml └── src └── f5_tts ├── api.py ├── eval ├── README.md ├── ecapa_tdnn.py ├── eval_infer_batch.py ├── eval_infer_batch.sh ├── eval_librispeech_test_clean.py ├── eval_seedtts_testset.py └── utils_eval.py ├── infer ├── README.md ├── 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 │ ├── dit.py │ ├── mmdit.py │ └── unett.py ├── cfm.py ├── dataset.py ├── modules.py ├── trainer.py └── utils.py ├── scripts ├── count_max_epoch.py └── count_params_gflops.py └── train ├── README.md ├── datasets ├── prepare_csv_wavs.py ├── prepare_emilia.py └── prepare_wenetspeech4tts.py ├── finetune_cli.py ├── finetune_gradio.py └── train.py /.github/workflows/pre-commit.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/.github/workflows/pre-commit.yaml -------------------------------------------------------------------------------- /.github/workflows/publish-docker-image.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/.github/workflows/publish-docker-image.yaml -------------------------------------------------------------------------------- /.github/workflows/sync-hf.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/.github/workflows/sync-hf.yaml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/.gitmodules -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/Dockerfile -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/LICENSE -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include .\src\f5_tts\infer\examples\vocab.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/README.md -------------------------------------------------------------------------------- /ckpts/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/ckpts/README.md -------------------------------------------------------------------------------- /data/Emilia_ZH_EN_pinyin/vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/data/Emilia_ZH_EN_pinyin/vocab.txt -------------------------------------------------------------------------------- /data/librispeech_pc_test_clean_cross_sentence.lst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/data/librispeech_pc_test_clean_cross_sentence.lst -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/pyproject.toml -------------------------------------------------------------------------------- /ruff.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/ruff.toml -------------------------------------------------------------------------------- /src/f5_tts/api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/api.py -------------------------------------------------------------------------------- /src/f5_tts/eval/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/eval/README.md -------------------------------------------------------------------------------- /src/f5_tts/eval/ecapa_tdnn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/eval/ecapa_tdnn.py -------------------------------------------------------------------------------- /src/f5_tts/eval/eval_infer_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/eval/eval_infer_batch.py -------------------------------------------------------------------------------- /src/f5_tts/eval/eval_infer_batch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/eval/eval_infer_batch.sh -------------------------------------------------------------------------------- /src/f5_tts/eval/eval_librispeech_test_clean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/eval/eval_librispeech_test_clean.py -------------------------------------------------------------------------------- /src/f5_tts/eval/eval_seedtts_testset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/eval/eval_seedtts_testset.py -------------------------------------------------------------------------------- /src/f5_tts/eval/utils_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/eval/utils_eval.py -------------------------------------------------------------------------------- /src/f5_tts/infer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/README.md -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/basic/basic.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/examples/basic/basic.toml -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/basic/basic_ref_en.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/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/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/examples/basic/basic_ref_zh.wav -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/multi/country.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/examples/multi/country.flac -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/multi/main.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/examples/multi/main.flac -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/multi/story.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/examples/multi/story.toml -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/multi/story.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/examples/multi/story.txt -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/multi/town.flac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/examples/multi/town.flac -------------------------------------------------------------------------------- /src/f5_tts/infer/examples/vocab.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/examples/vocab.txt -------------------------------------------------------------------------------- /src/f5_tts/infer/infer_cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/infer_cli.py -------------------------------------------------------------------------------- /src/f5_tts/infer/infer_gradio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/infer_gradio.py -------------------------------------------------------------------------------- /src/f5_tts/infer/speech_edit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/speech_edit.py -------------------------------------------------------------------------------- /src/f5_tts/infer/utils_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/infer/utils_infer.py -------------------------------------------------------------------------------- /src/f5_tts/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/model/__init__.py -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/model/backbones/README.md -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/dit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/model/backbones/dit.py -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/mmdit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/model/backbones/mmdit.py -------------------------------------------------------------------------------- /src/f5_tts/model/backbones/unett.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/model/backbones/unett.py -------------------------------------------------------------------------------- /src/f5_tts/model/cfm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/model/cfm.py -------------------------------------------------------------------------------- /src/f5_tts/model/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/model/dataset.py -------------------------------------------------------------------------------- /src/f5_tts/model/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/model/modules.py -------------------------------------------------------------------------------- /src/f5_tts/model/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/model/trainer.py -------------------------------------------------------------------------------- /src/f5_tts/model/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/model/utils.py -------------------------------------------------------------------------------- /src/f5_tts/scripts/count_max_epoch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/scripts/count_max_epoch.py -------------------------------------------------------------------------------- /src/f5_tts/scripts/count_params_gflops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/scripts/count_params_gflops.py -------------------------------------------------------------------------------- /src/f5_tts/train/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/train/README.md -------------------------------------------------------------------------------- /src/f5_tts/train/datasets/prepare_csv_wavs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/train/datasets/prepare_csv_wavs.py -------------------------------------------------------------------------------- /src/f5_tts/train/datasets/prepare_emilia.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/train/datasets/prepare_emilia.py -------------------------------------------------------------------------------- /src/f5_tts/train/datasets/prepare_wenetspeech4tts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/train/datasets/prepare_wenetspeech4tts.py -------------------------------------------------------------------------------- /src/f5_tts/train/finetune_cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/train/finetune_cli.py -------------------------------------------------------------------------------- /src/f5_tts/train/finetune_gradio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/train/finetune_gradio.py -------------------------------------------------------------------------------- /src/f5_tts/train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JarodMica/F5-TTS/HEAD/src/f5_tts/train/train.py --------------------------------------------------------------------------------