1
0
mirror of synced 2024-11-30 18:24:32 +01:00
Retrieval-based-Voice-Conve.../README.md

145 lines
6.6 KiB
Markdown
Raw Normal View History

2023-04-27 18:16:38 +02:00
<div align="center">
<h1>Retrieval-based-Voice-Conversion-WebUI</h1>
一个基于VITS的简单易用的语音转换变声器框架<br><br>
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>
2023-06-22 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)
2023-06-24 10:41:22 +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)
2023-06-28 09:29:47 +02:00
[**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://huggingface.co/spaces/Ricecake123/RVC-demo)
2023-05-10 17:39:04 +02:00
2023-04-27 18:16:38 +02:00
</div>
------
2023-08-27 15:08:37 +02:00
[**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)) | [**Türkçe**](./docs/tr/README.tr.md)
2023-04-27 18:16:38 +02:00
2023-06-19 14:11:41 +02:00
点此查看我们的[演示视频](https://www.bilibili.com/video/BV1pm4y1z7Gm/) !
2023-06-11 15:56:06 +02:00
2023-06-28 09:29:47 +02:00
> 使用了RVC的实时语音转换: [w-okada/voice-changer](https://github.com/w-okada/voice-changer)
2023-04-27 18:16:38 +02:00
> 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
2023-08-13 18:10:26 +02:00
> 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。
2023-04-27 18:16:38 +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
2023-08-13 18:01:47 +02:00
+ A卡I卡加速支持
2023-04-27 18:16:38 +02:00
## 环境配置
2023-07-29 16:44:36 +02:00
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
2023-07-29 16:44:36 +02:00
(Windows/Linux)
首先通过 pip 安装主要依赖:
2023-04-27 18:16:38 +02:00
```bash
# 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/
pip install torch torchvision torchaudio
#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
#pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117
2023-07-29 16:44:36 +02:00
```
2023-04-27 18:16:38 +02:00
2023-07-29 16:44:36 +02:00
可以使用 poetry 来安装依赖:
```bash
2023-04-27 18:16:38 +02:00
# 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
curl -sSL https://install.python-poetry.org | python3 -
# 通过poetry安装依赖
poetry install
```
2023-07-29 16:44:36 +02:00
你也可以通过 pip 来安装依赖:
2023-05-10 17:27:33 +02:00
```bash
2023-08-13 18:01:47 +02:00
N卡
2023-05-10 17:27:33 +02:00
pip install -r requirements.txt
2023-08-13 18:01:47 +02:00
A卡/I卡
pip install -r requirements-dml.txt
2023-05-10 17:27:33 +02:00
```
2023-04-27 18:16:38 +02:00
2023-07-29 16:44:36 +02:00
------
Mac 用户可以通过 `run.sh` 来安装依赖:
```bash
sh ./run.sh
```
2023-04-27 18:16:38 +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。
你可以从我们的[Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)下载到这些模型。
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:
```bash
2023-08-28 09:00:51 +02:00
./assets/hubert/hubert_base.pt
2023-04-27 18:16:38 +02:00
2023-08-28 09:00:51 +02:00
./assets/pretrained
2023-04-27 18:16:38 +02:00
2023-08-28 09:00:51 +02:00
./assets/uvr5_weights
2023-04-27 18:16:38 +02:00
想测试v2版本模型的话需要额外下载
2023-05-14 09:19:35 +02:00
2023-08-28 09:00:51 +02:00
./assets/pretrained_v2
2023-05-14 09:19:35 +02:00
2023-07-29 16:44:36 +02:00
如果你正在使用Windows则你可能需要这个文件若ffmpeg和ffprobe已安装则跳过; ubuntu/debian 用户可以通过apt install ffmpeg来安装这2个库, Mac 用户则可以通过brew install ffmpeg来安装 (需要预先安装brew)
2023-04-27 18:16:38 +02:00
./ffmpeg
https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe
2023-04-27 18:16:38 +02:00
./ffprobe
https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe
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
https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt
2023-08-13 18:01:47 +02:00
A卡I卡用户需要的dml环境要请下载
https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx
2023-04-27 18:16:38 +02:00
```
之后使用以下指令来启动WebUI:
```bash
python infer-web.py
```
2023-07-29 16:44:36 +02:00
如果你正在使用Windows 或 macOS你可以直接下载并解压`RVC-beta.7z`,前者可以运行`go-web.bat`以启动WebUI后者则运行命令`sh ./run.sh`以启动WebUI。
2023-04-27 18:16:38 +02:00
仓库内还有一份`小白简易教程.doc`以供参考。
## 参考项目
+ [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)
+ [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).
2023-04-27 18:16:38 +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>