mirror of
https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI.git
synced 2026-06-05 01:10:22 +08:00
a55e81060225d7805a2bf01ca484c1917eba4be8
Retrieval-based-Voice-Conversion-WebUI
缺失的2个文件夹和2个文件:
hubert_base.pt
ffmpeg(自己确保ffmpeg命令能执行就行)
pretrained文件夹
uvr5_weights文件夹
文件太大github传不动,去huggingface上下https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main
按照requirements.txt用pip装好环境,python infer-web.py就能用了
根据经验,librosa numpy和numba三个包最好写死版本否则容易有坑,其他的包版本不太重要
Description
Easily train a good VC model with voice data <= 10 mins!
audio-analysisaudio-processingconversionconverterrmvpervcrvc-projectvcvoicevoice-changervoice-conversionvoicechangervoicecloningvoiceconversion
Readme
AGPL-3.0
16 MiB
Languages
Python
98.9%
Go
0.5%
Dockerfile
0.5%
Shell
0.1%