mirror of
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
synced 2026-08-29 01:59:23 +02:00
132126af72
Add the five-model MSST backend, CUDA precision reuse, fast MP3/M4A encoding, PyAV compatibility fixes, remote dependencies, model configs, Hugging Face download guidance, and multilingual pymss credits. Remove the obsolete tools/uvr5 implementation.
70 lines
2.3 KiB
Plaintext
70 lines
2.3 KiB
Plaintext
# Python 3.12 x64 / Windows + Linux / NVIDIA CUDA 12.8
|
|
#
|
|
# Install in two stages from the project root. Torch and Torchaudio are NOT
|
|
# listed below, so the second command cannot replace the verified cu128 pair.
|
|
#
|
|
# Stage 1 - install the matching CUDA 12.8 pair (Torch must stay below 2.8):
|
|
# python -m pip install torch==2.7.1+cu128 torchaudio==2.7.1+cu128 --index-url https://mirrors.nju.edu.cn/pytorch/whl/cu128 --extra-index-url https://mirrors.pku.edu.cn/pypi/simple
|
|
#
|
|
# Stage 2 - install all remaining project dependencies:
|
|
# python -m pip install -r requirments_cu128_py312.txt
|
|
# Windows portable runtime users may replace `python` with `runtime\python.exe -I`.
|
|
|
|
--index-url https://mirrors.pku.edu.cn/pypi/simple
|
|
|
|
# Packaging support. Gradio 3.14 still imports pkg_resources, so Setuptools
|
|
# must remain on the last generation that provides it.
|
|
setuptools>=75.0,<81
|
|
wheel>=0.45,<1
|
|
packaging>=24.0
|
|
|
|
# Direct project dependencies. Upper bounds are used only where a newer major
|
|
# release changes an API/ABI used by this project or breaks NumPy 1.x support.
|
|
av>=15.1.0,<16
|
|
einops>=0.8.0,<1
|
|
faiss-cpu>=1.13.0,<2
|
|
ffmpeg-python>=0.2.0,<1
|
|
FreeSimpleGUI>=5.1.0,<5.2
|
|
librosa>=0.10.2,<0.11
|
|
local-attention>=1.11.0,<2
|
|
matplotlib>=3.8.2,<4
|
|
networkx>=3.2.0,<4
|
|
numpy>=1.26.4,<2
|
|
|
|
# Five-model MSST inference backend. Install both packages from the index;
|
|
# local wheel paths are intentionally not used by this requirements file.
|
|
pymss==2.0.14
|
|
pymss-core==0.1.4
|
|
|
|
# ONNX Runtime 1.19.x uses the CUDA 12 / cuDNN 9 provider ABI. Later current
|
|
# releases have moved to CUDA 13, so this compatibility window is intentional.
|
|
onnxruntime-gpu>=1.19.2,<1.20
|
|
coloredlogs>=15.0,<16
|
|
|
|
opencv-python-headless>=4.10.0,<5
|
|
praat-parselmouth>=0.4.5,<1
|
|
PyYAML>=6.0.1
|
|
scikit-learn>=1.6.0,<2
|
|
scipy>=1.13.1,<2
|
|
sounddevice>=0.5.0,<1
|
|
soundfile>=0.13.0,<1
|
|
tensorboard>=2.19.0
|
|
torchfcpe>=0.0.4,<0.1
|
|
tqdm>=4.67.0,<5
|
|
transformers>=4.49.0,<4.50
|
|
|
|
# Gradio 3.14 API compatibility. Newer Gradio/FastAPI/Pydantic generations
|
|
# changed component, event, generator, request and launch behavior used here.
|
|
gradio>=3.14.0,<3.15
|
|
altair>=4.2.0,<5
|
|
anyio>=3.6.2,<4
|
|
fastapi>=0.88.0,<0.100
|
|
httpx>=0.23.0,<0.24
|
|
markdown-it-py>=2.2.0,<3
|
|
mdit-py-plugins>=0.3.3,<0.4
|
|
pydantic>=1.10.13,<2
|
|
pyparsing>=3.0.9,<3.1
|
|
starlette>=0.22.0,<0.28
|
|
uvicorn>=0.20.0,<0.23
|
|
websockets>=10.4,<11
|