---
title: Bert-VITS2-demucs-funasr
canonical_url: "https://www.modelscope.cn/models/buzhidaozhanghaoming/Bert-VITS2-demucs-funasr"
md_url: "https://www.modelscope.cn/models/buzhidaozhanghaoming/Bert-VITS2-demucs-funasr.md"
repository: buzhidaozhanghaoming/Bert-VITS2-demucs-funasr
last_updated: 2023-11-25
license: "Apache License 2.0"
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
library_name:
  - tensorflow
  - pytorch
frameworks:
  - Pytorch
language:
  - zh
  - en
downloads: 698
stars: 20
tags:
  - Bert-VITS2
---

# Bert-VITS2-demucs-funasr

> Bert-VITS2-demucs-funasr - buzhidaozhanghaoming 在 ModelScope 开源的模型。Bert-VITS2-demucs-funasr，3个软件实现的语音克隆

buzhidaozhanghaoming/Bert-VITS2-demucs-funasr 是 ModelScope 魔搭社区上的text-to-speech模型，采用 Apache License 2.0 许可。

- **Repository**: buzhidaozhanghaoming/Bert-VITS2-demucs-funasr
- **License**: Apache License 2.0
- **Tasks**: text-to-speech
- **Tags**: Bert-VITS2
- **Downloads**: 698
- **Stars**: 20
- **Last updated**: 2023-11-25

Source: https://www.modelscope.cn/models/buzhidaozhanghaoming/Bert-VITS2-demucs-funasr

---

# Bert-VITS2-demucs-funasr
安装在Ubuntu22.04

底模默认使用2.0.2-fix版本，有1.1.1版本存档

程序使用1.1.1版本（能用就不换成高版本了）

git下载
```shell
git lfs install
git clone https://www.modelscope.cn/buzhidaozhanghaoming/Bert-VITS2-demucs-funasr.git
```
##安装软件
```shell
tar -xf Bert-VITS2.tar.xz
tar -xf logs.tar.xz
mv logs Bert-VITS2
pip install -r Bert-VITS2/requirements.txt
sudo apt install cmake -y
pip insteall pip -y
python3 -m pip install -U demucs #安装demucs #人声分离,最好不要使用
pip3 install -U funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple #安装Funasr，识别文字
pip3 install -U modelscope -i https://mirror.sjtu.edu.cn/pypi/web/simple 
git clone https://github.com/flutydeer/audio-slicer.git #安装音频切片机
sudo cp Bert-VITS2/slicer2_run.py audio-slicer     #复制slicer2_run.py到audio-slicer
```

##生成项目
```shell
cd Bert-VITS2
sh mkname.sh peng#生成项目文件夹
```

##处理wav文件
复制原声wav文件到wavs/peng/
```shell
python3 ../audio-slicer/slicer2_run.py --out raw/peng/ wavs/peng/   #执行分割wav
python3 funasr_run.py raw/peng/  #生成lab文件
```
核对wav与lab文字是否正确

##训练
```shell
python3 training.py peng
```

##断点继续训练
```shell
python3 training_breakPointContinue.py
```

##修改训练参数
```shell
vim configs/config.json   
```