Cool_Tools/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of synced 2024-11-15 11:23:21 +01:00
Code Releases Wiki Activity
Voice data <= 10 mins can also be used to train a good VC model!
11 Commits 2 Branches 7 Tags 84 MiB
Python 92.4%
Jupyter Notebook 4.5%
Batchfile 2.1%
Shell 0.6%
Dockerfile 0.4%
a55e810602
Go to file
liujing04 a55e810602
Update README.md
2023-03-31 18:14:21 +08:00
configs Add files via upload 2023-03-31 17:49:09 +08:00
infer Add files via upload 2023-03-31 17:49:09 +08:00
infer_pack Add files via upload 2023-03-31 17:47:00 +08:00
train Add files via upload 2023-03-31 17:47:00 +08:00
uvr5_pack Add files via upload 2023-03-31 17:47:00 +08:00
weights Create ... 2023-03-31 18:04:33 +08:00
config.py Add files via upload 2023-03-31 17:54:38 +08:00
extract_f0_print.py Add files via upload 2023-03-31 17:54:38 +08:00
extract_feature_print.py Add files via upload 2023-03-31 17:54:38 +08:00
infer_uvr5.py Add files via upload 2023-03-31 17:54:38 +08:00
infer-web.py Add files via upload 2023-03-31 17:54:38 +08:00
LICENSE Initial commit 2023-03-27 17:59:11 +08:00
my_utils.py Add files via upload 2023-03-31 17:54:38 +08:00
README.md Update README.md 2023-03-31 18:14:21 +08:00
requirements.txt Add files via upload 2023-03-31 17:54:38 +08:00
slicer2.py Add files via upload 2023-03-31 17:54:38 +08:00
train_nsf_sim_cache_sid_load_pretrain.py Add files via upload 2023-03-31 17:54:38 +08:00
trainset_preprocess_pipeline_print.py Add files via upload 2023-03-31 17:49:09 +08:00
vc_infer_pipeline.py Add files via upload 2023-03-31 17:49:09 +08:00
使用需遵守的协议-LICENSE.txt Add files via upload 2023-03-31 17:49:09 +08:00

README.md

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

宣传视频：https://www.bilibili.com/video/BV1pm4y1z7Gm/