mirror of
https://github.com/SWivid/F5-TTS.git
synced 2025-12-25 20:34:27 -08:00
c4eee0f96b
* group files in f5_tts directory * add setup.py * use global imports * simplify demo * add install directions for library mode * fix old huggingface_hub version constraint * move finetune to package * change imports to f5_tts.model * bump version * fix bad merge * Update inference-cli.py * fix HF space * reformat * fix utils.py vocab.txt import * fix format * adapt README for f5_tts package structure * simplify app.py * add gradio.Dockerfile and workflow * refactored for pyproject.toml * refactored for pyproject.toml * added in reference to packaged files * use fork for testing docker image * added in reference to packaged files * minor tweaks * fixed inference-cli.toml path * fixed inference-cli.toml path * fixed inference-cli.toml path * fixed inference-cli.toml path * refactor eval_infer_batch.py * fix typo * added eval_infer_batch to scripts --------- Co-authored-by: Roberts Slisans <rsxdalv@gmail.com> Co-authored-by: Adam Kessel <adam@rosi-kessel.org> Co-authored-by: Roberts Slisans <roberts.slisans@gmail.com>
53 lines
1.3 KiB
TOML
53 lines
1.3 KiB
TOML
[build-system]
|
|
requires = ["setuptools >= 61.0", "setuptools-scm>=8.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "f5-tts"
|
|
dynamic = ["version"]
|
|
description = "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
|
|
readme = "README.md"
|
|
classifiers = [
|
|
"License :: OSI Approved :: MIT License",
|
|
"Operating System :: OS Independent",
|
|
"Programming Language :: Python :: 3",
|
|
]
|
|
dependencies = [
|
|
"accelerate>=0.33.0",
|
|
"cached_path @ git+https://github.com/rsxdalv/cached_path@main",
|
|
"click",
|
|
"datasets",
|
|
"einops>=0.8.0",
|
|
"einx>=0.3.0",
|
|
"ema_pytorch>=0.5.2",
|
|
"gradio",
|
|
"jieba",
|
|
"librosa",
|
|
"matplotlib",
|
|
"numpy<=1.26.4",
|
|
"pydub",
|
|
"pypinyin",
|
|
"safetensors",
|
|
"soundfile",
|
|
"tomli",
|
|
"torch>=2.0.0",
|
|
"torchaudio>=2.0.0",
|
|
"torchdiffeq",
|
|
"tqdm>=4.65.0",
|
|
"transformers",
|
|
"vocos",
|
|
"wandb",
|
|
"x_transformers>=1.31.14",
|
|
]
|
|
|
|
[[project.authors]]
|
|
name = "Yushen Chen and Zhikang Niu and Ziyang Ma and Keqi Deng and Chunhui Wang and Jian Zhao and Kai Yu and Xie Chen"
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/SWivid/F5-TTS"
|
|
|
|
[project.scripts]
|
|
"finetune-cli" = "f5_tts.finetune_cli:main"
|
|
"inference-cli" = "f5_tts.inference_cli:main"
|
|
"eval_infer_batch" = "f5_tts.scripts.eval_infer_batch:main"
|