mirror of
https://github.com/index-tts/index-tts.git
synced 2026-08-28 23:01:17 +08:00
nanaoto
3376228d4b
* fix: repair Linux installs and README commands that fail on a clean machine Verified on a Linux GPU box using a fresh .venv and a separate UV_CACHE_DIR, since a warm cache hides every one of these. pyproject.toml: - triton-windows had no platform marker, so `uv sync --extra accel` (or --all-extras) aborted on Linux: the package only publishes win_amd64 wheels. Linux already gets `triton` as a torch dependency. - Replace `no-build-isolation-package` with `extra-build-dependencies`. That mode uses `.venv` itself as the build environment, and a fresh `.venv` has no setuptools yet, so deepspeed failed with `ModuleNotFoundError: No module named 'setuptools'` on any clean machine. Injecting torch with `match-runtime` keeps the CUDA-enabled build inputs while leaving isolation (and its setuptools) in place. It also lets flash-attn resolve a prebuilt wheel from its own torch version and C++ ABI flag instead of invoking nvcc. README (and the zh/ja/es/ar translations): - `examples/09.wav` does not exist in the demo space and is not in cases.jsonl; the on-demand download fetches `voice_09.wav`. - `huggingface-hub` dropped its `cli` extra, so the install line warned. - Example audio is fetched by the WebUI only, not by `infer_v2_5.py`, whose default --prompt_wav is `examples/voice_01.wav`. Say so and give a one-liner to fetch it. - Drop `uv run indextts/infer_v2.py`: it is a benchmark loop hardcoded to `checkpoints/`, so with the documented `checkpoints_2` layout it dies on `vocab_file checkpoints/bpe.model does not exist`. - `use_emo_text=True` needs `use_qwen_emo=True` at construction, which the init example omits. webui.py: title and arXiv badge were hardcoded to IndexTTS2, so the 2.5 UI announced itself as 2 and linked the 2.0 paper. * docs: install huggingface-hub without extras `hf-xet` is an unconditional base dependency of huggingface-hub on x86_64, arm64 and aarch64, not just an extra, so `[hf_xet]` selected nothing that the plain package does not already pull in. The plain install still provides the `hf`, `huggingface-cli` and `tiny-agents` executables. Applies to the remaining seven translations and archived READMEs too, which still carried the `[cli,hf_xet]` form whose `cli` extra no longer exists. * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: nanaoto <10inspiral@gmail.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
144 lines
4.6 KiB
TOML
144 lines
4.6 KiB
TOML
[project]
|
|
name = "indextts"
|
|
version = "2.0.0"
|
|
description = "IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech"
|
|
authors = [{ name = "Bilibili IndexTTS Team" }]
|
|
license = "LicenseRef-Bilibili-IndexTTS"
|
|
license-files = ["LICEN[CS]E*", "INDEX_MODEL_LICENSE*"]
|
|
readme = "README.md"
|
|
classifiers = [
|
|
"Development Status :: 5 - Production/Stable",
|
|
|
|
"Intended Audience :: Science/Research",
|
|
"Intended Audience :: Developers",
|
|
|
|
"Topic :: Scientific/Engineering",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
|
|
"Natural Language :: English",
|
|
"Natural Language :: Chinese (Simplified)",
|
|
|
|
"Programming Language :: Python :: 3",
|
|
|
|
"Operating System :: OS Independent",
|
|
]
|
|
requires-python = ">=3.10,<3.12"
|
|
dependencies = [
|
|
# IMPORTANT: Always run `uv lock` or `uv lock --upgrade` to resolve dependencies
|
|
# and update the lockfile after editing anything below.
|
|
# WARNING: Ensure that you don't have a local `uv.toml` which overrides PyPI
|
|
# while generating the lockfile: https://github.com/astral-sh/uv/issues/15741
|
|
"accelerate==1.8.1",
|
|
"cn2an==0.5.22",
|
|
"cython==3.0.7",
|
|
"descript-audiotools==0.7.2",
|
|
"einops>=0.8.1",
|
|
"ffmpeg-python==0.2.0",
|
|
"fugashi>=1.2.0",
|
|
"unidic-lite>=1.0.0",
|
|
"g2p-en==2.1.0",
|
|
"jieba==0.42.1",
|
|
"json5==0.10.0",
|
|
"keras==2.9.0",
|
|
"librosa==0.10.2.post1",
|
|
"matplotlib==3.10.0",
|
|
"modelscope==1.27.0",
|
|
"munch==4.0.0",
|
|
"numba==0.63.0",
|
|
"numpy==2.2.6",
|
|
"omegaconf>=2.3.0",
|
|
"opencv-python==4.9.0.80",
|
|
"pandas==2.3.2",
|
|
"safetensors==0.5.2",
|
|
"sentencepiece>=0.2.1",
|
|
"tensorboard==2.20.0",
|
|
"textstat>=0.7.10",
|
|
"tokenizers==0.21.0",
|
|
"torch==2.8.*",
|
|
"torchaudio==2.8.*",
|
|
"requests>=2.28",
|
|
"tqdm>=4.67.1",
|
|
"transformers==4.52.1",
|
|
"openai-whisper>=20231117",
|
|
"fugashi[unidic-lite]",
|
|
|
|
# Use "wetext" on Windows/Mac, otherwise "WeTextProcessing" on Linux.
|
|
"wetext>=0.0.9; sys_platform != 'linux'",
|
|
"WeTextProcessing; sys_platform == 'linux'",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
# To install the WebUI support, use `uv sync --extra webui` (or `--all-extras`).
|
|
webui = [
|
|
"gradio==5.45.0",
|
|
]
|
|
# To install the DeepSpeed support, use `uv sync --extra deepspeed` (or `--all-extras`).
|
|
deepspeed = [
|
|
"deepspeed==0.17.1",
|
|
]
|
|
# To install the GPT2 acceleration engine, use `uv sync --extra accel` (or `--all-extras`).
|
|
# NOTE: flash-attn 2.8.3.post1 also requires triton at import time on Windows.
|
|
accel = [
|
|
"flash-attn==2.8.3.post1",
|
|
"nvidia-cuda-runtime-cu12",
|
|
"nvidia-cudnn-cu12",
|
|
"triton-windows==3.1.0.post17; sys_platform == 'win32'",
|
|
]
|
|
# To install torch.compile support for s2mel, use `uv sync --extra torch_compile` (or `--all-extras`).
|
|
# On Windows this is satisfied by the triton-windows package above.
|
|
torch_compile = [
|
|
"triton-windows==3.1.0.post17; sys_platform == 'win32'",
|
|
]
|
|
test = [
|
|
"pytest>=7.0",
|
|
]
|
|
|
|
[tool.pytest.ini_options]
|
|
markers = [
|
|
"gpu: tests that require GPU and model checkpoints (deselect with '-m not gpu')",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/index-tts/index-tts"
|
|
Repository = "https://github.com/index-tts/index-tts.git"
|
|
|
|
[project.scripts]
|
|
# Set the installed binary names and entry points.
|
|
indextts = "indextts.cli:main"
|
|
indextts2 = "indextts.cli_v2:main"
|
|
|
|
[build-system]
|
|
# How to build the project as a CLI tool or PyPI package.
|
|
# NOTE: Use `uv tool install -e .` to install the package as a CLI tool.
|
|
requires = ["hatchling >= 1.27.0"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.uv.extra-build-dependencies]
|
|
# Build against our CUDA-enabled PyTorch: DeepSpeed picks its GPU targets from it,
|
|
# and flash-attn reads its version and C++ ABI flag to fetch a matching prebuilt
|
|
# wheel instead of compiling.
|
|
deepspeed = [{ requirement = "torch", match-runtime = true }]
|
|
flash-attn = [{ requirement = "torch", match-runtime = true }]
|
|
|
|
[tool.uv.sources]
|
|
# Install PyTorch with CUDA support on Linux/Windows (CUDA doesn't exist for Mac).
|
|
# NOTE: We must explicitly request them as `dependencies` above. These improved
|
|
# versions will not be selected if they're only third-party dependencies.
|
|
torch = [
|
|
{ index = "pytorch-cuda", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
|
|
]
|
|
torchaudio = [
|
|
{ index = "pytorch-cuda", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
|
|
]
|
|
torchvision = [
|
|
{ index = "pytorch-cuda", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
|
|
]
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch-cuda"
|
|
# Use PyTorch built for NVIDIA Toolkit version 12.8.
|
|
# Available versions: https://pytorch.org/get-started/locally/
|
|
url = "https://download.pytorch.org/whl/cu128"
|
|
# Only use this index when explicitly requested by `tool.uv.sources`.
|
|
explicit = true
|