OPENGIT
/
Retrieval-based-Voice-Conversion-WebUI
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
一个基于VITS的简单易用的变声框架
41 Commits 2 Branches 7 Tags 70 MiB
Python 92%
Jupyter Notebook 4.7%
Batchfile 2.3%
Shell 0.6%
Dockerfile 0.4%
Go to file
vior bdf238cccb fix 'weights/[]' 2023-04-05 22:58:49 +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 删除无用文件，增加--colab启动选项 2023-04-01 15:02:53 +08:00
pretrained 删除无用文件，增加--colab启动选项 2023-04-01 15:02:53 +08:00
train 删除无用文件，增加--colab启动选项 2023-04-01 15:02:53 +08:00
uvr5_pack 删除无用文件，增加--colab启动选项 2023-04-01 15:02:53 +08:00
uvr5_weights 删除无用文件，增加--colab启动选项 2023-04-01 15:02:53 +08:00
weights 删除无用文件，增加--colab启动选项 2023-04-01 15:02:53 +08:00
.gitignore fix: train step2a & add arg --port --pycmd --noparallel 2023-04-01 16:42:19 +08:00
LICENSE Initial commit 2023-03-27 17:59:11 +08:00
README.md add colab 2023-04-01 19:58:33 +08:00
Retrieval_based_Voice_Conversion_WebUI.ipynb 为笔记本添加更多功能 2023-04-02 16:07:02 +08:00
config.py fix: train step2a & add arg --port --pycmd --noparallel 2023-04-01 16:42:19 +08:00
envfilescheck.bat Add a batch file for windows user to download requearment files automated by using aria2. 2023-04-04 00:23:39 +08:00
extract_f0_print.py Add files via upload 2023-03-31 17:54:38 +08:00
extract_feature_print.py fix: extract freture cannot run on pure cpu 2023-04-01 17:05:48 +08:00
infer-web.py fix 'weights/[]' 2023-04-05 22:58:49 +08:00
infer_uvr5.py Add files via upload 2023-03-31 17:54:38 +08:00
my_utils.py fix: train step2a & add arg --port --pycmd --noparallel 2023-04-01 16:42:19 +08:00
poetry.lock add poetry dependency file 2023-04-05 10:44:07 +08:00
pyproject.toml add poetry dependency file 2023-04-05 10:44:07 +08:00
requirments.txt Update requirments.txt 2023-04-05 20:29:04 +08:00
slicer2.py fix: train step2a & add arg --port --pycmd --noparallel 2023-04-01 16:42:19 +08:00
train_nsf_sim_cache_sid_load_pretrain.py fix 2023-04-01 17:29:14 +08:00
trainset_preprocess_pipeline_print.py fix: train step2a & add arg --port --pycmd --noparallel 2023-04-01 16:42:19 +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 fix: train step2a & add arg --port --pycmd --noparallel 2023-04-01 16:42:19 +08:00
小白简易教程.doc Add files via upload 2023-03-31 18:52:30 +08:00

README.md

Retrieval-based-Voice-Conversion-WebUI

Open In Colab

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

当然你也可以直接看看RVC-beta.7z这个文件→_→

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/

教程见小白简易教程.doc