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
Voice data <= 10 mins can also be used to train a good VC model!
audio-analysischangeconversational-aiconversionconverterretrieval-modelretrieve-datarvcsovitsso-vits-svcvcvitsvoicevoice-conversionvoiceconversionvoice-converter
Readme
MIT
84 MiB
Languages
Python
92.6%
Jupyter Notebook
4.4%
Batchfile
2.1%
Shell
0.6%
Dockerfile
0.3%