Mirrors/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-08-29 10:09:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

Replace UVR5 separation backend with pymss

Browse Source 
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.
This commit is contained in:
RVC-Boss
2026-07-23 01:40:12 +08:00
parent dbf85f721c
commit 132126af72
36 changed files with 943 additions and 3767 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
requirments_cu118_py312.txt
View File

@@ -31,6 +31,11 @@ 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 1.18.x is the CUDA 11 / cuDNN 8 generation with Python 3.12
# Windows wheels. The CUDA DLL packages are pinned because later cuDNN/CUDA
# majors are ABI-incompatible with this provider build.
@@ -43,7 +48,7 @@ nvidia-cufft-cu11==10.9.0.58
opencv-python-headless>=4.10.0,<5
praat-parselmouth>=0.4.5,<1
PyYAML>=6.0
PyYAML>=6.0.1
scikit-learn>=1.6.0,<2
scipy>=1.13.1,<2
sounddevice>=0.5.0,<1