2023-04-27 18:16:38 +02:00
< div align = "center" >
< h1 > Retrieval-based-Voice-Conversion-WebUI< / h1 >
2023-10-06 13:11:58 +02:00
一个基于VITS的简单易用的变声框架< br > < br >
2023-04-27 18:16:38 +02:00
2023-08-09 13:32:49 +02:00
[![madewithlove](https://img.shields.io/badge/made_with-%E2%9D%A4-red?style=for-the-badge& labelColor=orange
)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)
2023-04-27 18:16:38 +02:00
< img src = "https://counter.seku.su/cmoe?name=rvc&theme=r34" / > < br >
2023-09-18 16:50:30 +02:00
2023-06-22 08:37:09 +02:00
[![Open In Colab ](https://img.shields.io/badge/Colab-F9AB00?style=for-the-badge&logo=googlecolab&color=525252 )](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)
2023-09-18 16:50:30 +02:00
[![Licence ](https://img.shields.io/badge/LICENSE-MIT-green.svg?style=for-the-badge )](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
2023-04-27 18:16:38 +02:00
[![Huggingface ](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge )](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
[![Discord ](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white )](https://discord.gg/HcsmBBGyVk)
2023-10-29 05:36:00 +01:00
[**更新日志** ](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/Changelog_CN.md ) | [**常见问题解答** ](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/wiki/%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98%E8%A7%A3%E7%AD%94 ) | [**AutoDL·5毛钱训练AI歌手** ](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/wiki/Autodl%E8%AE%AD%E7%BB%83RVC%C2%B7AI%E6%AD%8C%E6%89%8B%E6%95%99%E7%A8%8B ) | [**对照实验记录** ](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/wiki/Autodl%E8%AE%AD%E7%BB%83RVC%C2%B7AI%E6%AD%8C%E6%89%8B%E6%95%99%E7%A8%8B](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/wiki/%E5%AF%B9%E7%85%A7%E5%AE%9E%E9%AA%8C%C2%B7%E5%AE%9E%E9%AA%8C%E8%AE%B0%E5%BD%95 )) | [**在线演示** ](https://modelscope.cn/studios/FlowerCry/RVCv2demo )
2023-09-18 16:50:30 +02:00
2024-01-14 07:35:05 +01:00
[**English** ](./docs/en/README.en.md ) | [**中文简体** ](./README.md ) | [**日本語** ](./docs/jp/README.ja.md ) | [**한국어** ](./docs/kr/README.ko.md ) ([**韓國語**](./docs/kr/README.ko.han.md)) | [**Français** ](./docs/fr/README.fr.md ) | [**Türkçe** ](./docs/tr/README.tr.md )
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
< / div >
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
> 底模使用接近50小时的开源高质量VCTK训练集训练, 无版权方面的顾虑, 请大家放心使用
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
> 请期待RVCv3的底模, 参数更大, 数据更大, 效果更好, 基本持平的推理速度, 需要训练数据量更少。
2023-06-11 15:56:06 +02:00
2023-12-28 16:52:10 +01:00
< table >
< tr >
< td align = "center" > 训练推理界面< / td >
< td align = "center" > 实时变声界面< / td >
< / tr >
< tr >
< td align = "center" > < img src = "https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/assets/129054828/092e5c12-0d49-4168-a590-0b0ef6a4f630" > < / td >
< td align = "center" > < img src = "https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/assets/129054828/730b4114-8805-44a1-ab1a-04668f3c30a6" > < / td >
< / tr >
< tr >
< td align = "center" > go-web.bat< / td >
< td align = "center" > go-realtime-gui.bat< / td >
< / tr >
< tr >
< td align = "center" > 可以自由选择想要执行的操作。< / td >
< td align = "center" > 我们已经实现端到端170ms延迟。如使用ASIO输入输出设备, 已能实现端到端90ms延迟, 但非常依赖硬件驱动支持。< / td >
< / tr >
< / table >
2023-04-27 18:16:38 +02:00
2023-09-18 16:50:30 +02:00
## 简介
本仓库具有以下特点
+ 使用top1检索替换输入源特征为训练集特征来杜绝音色泄漏
+ 即便在相对较差的显卡上也能快速训练
+ 使用少量数据进行训练也能得到较好结果(推荐至少收集10分钟低底噪语音数据)
+ 可以通过模型融合来改变音色(借助ckpt处理选项卡中的ckpt-merge)
+ 简单易用的网页界面
+ 可调用UVR5模型来快速分离人声和伴奏
+ 使用最先进的[人声音高提取算法InterSpeech2023-RMVPE](#参考项目)根绝哑音问题。效果最好( 显著地) 但比crepe_full更快、资源占用更小
+ A卡I卡加速支持
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
点此查看我们的[演示视频](https://www.bilibili.com/video/BV1pm4y1z7Gm/) !
2023-09-18 16:50:30 +02:00
## 环境配置
以下指令需在 Python 版本大于3.8的环境中执行。
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
### Windows/Linux/MacOS等平台通用方法
下列方法任选其一。
#### 1. 通过 pip 安装依赖
1. 安装Pytorch及其核心依赖, 若已安装则跳过。参考自: https://pytorch.org/get-started/locally/
2023-04-27 18:16:38 +02:00
```bash
pip install torch torchvision torchaudio
2023-12-28 17:23:16 +01:00
```
2. 如果是 win 系统 + Nvidia Ampere 架构(RTX30xx),根据 #21 的经验,需要指定 pytorch 对应的 cuda 版本
```bash
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117
```
3. 根据自己的显卡安装对应依赖
- N卡
```bash
pip install -r requirements.txt
```
- A卡/I卡
```bash
pip install -r requirements-dml.txt
```
- A卡ROCM(Linux)
```bash
pip install -r requirements-amd.txt
```
- I卡IPEX(Linux)
```bash
pip install -r requirements-ipex.txt
2023-07-29 16:44:36 +02:00
```
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
#### 2. 通过 poetry 来安装依赖
安装 Poetry 依赖管理工具,若已安装则跳过。参考自: https://python-poetry.org/docs/#installation
2023-07-29 16:44:36 +02:00
```bash
2023-04-27 18:16:38 +02:00
curl -sSL https://install.python-poetry.org | python3 -
```
2023-12-28 17:23:16 +01:00
通过poetry安装依赖
2023-05-10 17:27:33 +02:00
```bash
2023-12-28 17:23:16 +01:00
poetry install
2023-05-10 17:27:33 +02:00
```
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
### MacOS
可以通过 `run.sh` 来安装依赖
2023-07-29 16:44:36 +02:00
```bash
sh ./run.sh
```
2023-09-18 16:50:30 +02:00
## 其他预模型准备
RVC需要其他一些预模型来推理和训练。
2023-04-27 18:16:38 +02:00
2023-09-18 16:50:30 +02:00
你可以从我们的[Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)下载到这些模型。
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
### 1. 下载 assets
以下是一份清单, 包括了所有RVC所需的预模型和其他文件的名称。你可以在`tools`文件夹找到下载它们的脚本。
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
- ./assets/hubert/hubert_base.pt
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
- ./assets/pretrained
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
- ./assets/uvr5_weights
2023-05-14 09:19:35 +02:00
2023-12-28 17:23:16 +01:00
想使用v2版本模型的话, 需要额外下载
2023-05-14 09:19:35 +02:00
2023-12-28 17:23:16 +01:00
- ./assets/pretrained_v2
2023-07-11 06:02:30 +02:00
2023-12-28 17:23:16 +01:00
### 2. 安装 ffmpeg
若ffmpeg和ffprobe已安装则跳过。
2023-04-27 18:16:38 +02:00
2023-12-28 17:23:16 +01:00
#### Ubuntu/Debian 用户
```bash
sudo apt install ffmpeg
```
#### MacOS 用户
```bash
brew install ffmpeg
```
#### Windwos 用户
下载后放置在根目录。
- 下载[ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe)
2023-07-11 06:02:30 +02:00
2023-12-28 17:23:16 +01:00
- 下载[ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe)
2023-07-11 06:02:30 +02:00
2023-12-28 17:23:16 +01:00
### 3. 下载 rmvpe 人声音高提取算法所需文件
2023-08-13 18:01:47 +02:00
2023-12-28 17:23:16 +01:00
如果你想使用最新的RMVPE人声音高提取算法, 则你需要下载音高提取模型参数并放置于RVC根目录。
2023-08-13 18:01:47 +02:00
2023-12-28 17:23:16 +01:00
- 下载[rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
2023-09-18 16:50:30 +02:00
2023-12-28 17:23:16 +01:00
#### 下载 rmvpe 的 dml 环境(可选, A卡/I卡用户)
2023-10-06 11:14:33 +02:00
2023-12-28 17:23:16 +01:00
- 下载[rmvpe.onnx](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx)
2023-04-27 18:16:38 +02:00
2023-12-28 17:24:08 +01:00
### 4. AMD显卡Rocm(可选, 仅Linux)
2023-10-06 11:14:33 +02:00
如果你想基于AMD的Rocm技术在Linux系统上运行RVC, 请先在[这里](https://rocm.docs.amd.com/en/latest/deploy/linux/os-native/install.html)安装所需的驱动。
若你使用的是Arch Linux, 可以使用pacman来安装所需驱动:
````
pacman -S rocm-hip-sdk rocm-opencl-sdk
````
对于某些型号的显卡, 你可能需要额外配置如下的环境变量( 如: RX6700XT) :
````
export ROCM_PATH=/opt/rocm
export HSA_OVERRIDE_GFX_VERSION=10.3.0
````
同时确保你的当前用户处于`render`与`video`用户组内:
````
sudo usermod -aG render $USERNAME
sudo usermod -aG video $USERNAME
````
2023-12-28 17:23:16 +01:00
## 开始使用
### 直接启动
使用以下指令来启动 WebUI
2023-10-06 11:14:33 +02:00
```bash
python infer-web.py
```
2023-12-28 17:23:16 +01:00
### 使用整合包
下载并解压`RVC-beta.7z`
#### Windows 用户
双击`go-web.bat`
#### MacOS 用户
```bash
sh ./run.sh
```
### 对于需要使用IPEX技术的I卡用户(仅Linux)
```bash
source /opt/intel/oneapi/setvars.sh
```
2023-09-18 16:50:30 +02:00
## 参考项目
2023-04-27 18:16:38 +02:00
+ [ContentVec ](https://github.com/auspicious3000/contentvec/ )
+ [VITS ](https://github.com/jaywalnut310/vits )
+ [HIFIGAN ](https://github.com/jik876/hifi-gan )
+ [Gradio ](https://github.com/gradio-app/gradio )
+ [FFmpeg ](https://github.com/FFmpeg/FFmpeg )
+ [Ultimate Vocal Remover ](https://github.com/Anjok07/ultimatevocalremovergui )
+ [audio-slicer ](https://github.com/openvpi/audio-slicer )
2023-07-11 06:02:30 +02:00
+ [Vocal pitch extraction:RMVPE ](https://github.com/Dream-High/RMVPE )
+ The pretrained model is trained and tested by [yxlllc ](https://github.com/yxlllc/RMVPE ) and [RVC-Boss ](https://github.com/RVC-Boss ).
2023-09-18 16:50:30 +02:00
## 感谢所有贡献者作出的努力
2023-06-22 08:37:09 +02:00
< a href = "https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/graphs/contributors" target = "_blank" >
< img src = "https://contrib.rocks/image?repo=RVC-Project/Retrieval-based-Voice-Conversion-WebUI" / >
2023-04-27 18:16:38 +02:00
< / a >