mirror of
https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI.git
synced 2026-06-05 01:10:22 +08:00
docs: make english README the repository's default README (#38)
* docs: make english README the repository's default README some people might be scared off by a base README being in Chinese, so using a more universally known language like English seems to be more suited for open-source projects. i believe some people just come to the project, see the README and then they're frightened to even work on/with it this is a change curated by the #33 issue * docs: use MIT badge directly instead of relying on the repo link * docs: make READMEs grab the license badge directly via repo's specified license
This commit is contained in:
Alex Murkoff
GitHub
154
README.md
154
README.md
@@ -1,111 +1,113 @@
|
||||
<div align="center">
|
||||
|
||||
# Retrieval-based-Voice-Conversion-WebUI
|
||||
一个基于VITS的简单易用的变声框架<br><br>
|
||||
An easy-to-use voice conversion framework based on VITS.
|
||||
|
||||
|
||||
|
||||
[](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI)
|
||||
|
||||
|
||||
|
||||
[](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
|
||||
[](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)
|
||||
[](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
|
||||
|
||||
[](https://discord.gg/HcsmBBGyVk)
|
||||
|
||||
[**更新日志**](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/Changelog_CN.md) | [**常见问题解答**](https://github.com/fumiama/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/fumiama/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/fumiama/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/fumiama/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)
|
||||
[**Changelog**](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/Changelog_EN.md) | [**FAQ (Frequently Asked Questions)**](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/wiki/FAQ-(Frequently-Asked-Questions))
|
||||
|
||||
[**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) | [**Português**](./docs/pt/README.pt.md)
|
||||
[**English**](./README.md) | [**中文简体**](./docs/cn/README.cn.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) | [**Português**](./docs/pt/README.pt.md)
|
||||
|
||||
</div>
|
||||
|
||||
> 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
|
||||
> The base model is trained using nearly 50 hours of high-quality open-source VCTK training set. Therefore, there are no copyright concerns, please feel free to use.
|
||||
|
||||
> 请期待RVCv3的底模，参数更大，数据集更大，效果更好，基本持平的推理速度，需要训练数据量更少。
|
||||
> Please look forward to the base model of RVCv3 with larger parameters, larger dataset, better effects, basically flat inference speed, and less training data required.
|
||||
|
||||
> 由于某些地区无法直连Hugging Face，即使设法成功访问，速度也十分缓慢，特推出模型/整合包/工具的一键下载器，欢迎试用：[RVC-Models-Downloader](https://github.com/fumiama/RVC-Models-Downloader)
|
||||
> There's a [one-click downloader](https://github.com/fumiama/RVC-Models-Downloader) for models/integration packages/tools. Welcome to try.
|
||||
|
||||
| 训练推理界面 | 实时变声界面 |
|
||||
| Training and inference Webui | Real-time voice changing GUI |
|
||||
| :--------: | :---------: |
|
||||
|  |  |
|
||||
| go-web.bat | go-realtime-gui.bat |
|
||||
| 可以自由选择想要执行的操作。 | 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。|
|
||||
| You can freely choose the action you want to perform. | We have achieved an end-to-end latency of 170ms. With the use of ASIO input and output devices, we have managed to achieve an end-to-end latency of 90ms, but it is highly dependent on hardware driver support. |
|
||||
|
||||
## 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，效果更好，运行更快，资源占用更少
|
||||
+ A卡I卡加速支持
|
||||
## Features:
|
||||
+ Reduce tone leakage by replacing the source feature to training-set feature using top1 retrieval;
|
||||
+ Easy + fast training, even on poor graphics cards;
|
||||
+ Training with a small amounts of data (>=10min low noise speech recommended);
|
||||
+ Model fusion to change timbres (using ckpt processing tab->ckpt merge);
|
||||
+ Easy-to-use WebUI;
|
||||
+ UVR5 model to quickly separate vocals and instruments;
|
||||
+ High-pitch Voice Extraction Algorithm [InterSpeech2023-RMVPE](#Credits) to prevent a muted sound problem. Provides the best results (significantly) and is faster with lower resource consumption than Crepe_full;
|
||||
+ AMD/Intel graphics cards acceleration supported;
|
||||
+ Intel ARC graphics cards acceleration with IPEX supported.
|
||||
|
||||
点此查看我们的[演示视频](https://www.bilibili.com/video/BV1pm4y1z7Gm/) !
|
||||
Check out our [Demo Video](https://www.bilibili.com/video/BV1pm4y1z7Gm/) here!
|
||||
|
||||
## 环境配置
|
||||
### Python 版本限制
|
||||
> 建议使用 conda 管理 Python 环境
|
||||
## Environment Configuration
|
||||
### Python Version Limitation
|
||||
> It is recommended to use conda to manage the Python environment.
|
||||
|
||||
> 版本限制原因参见此[bug](https://github.com/facebookresearch/fairseq/issues/5012)
|
||||
> For the reason of the version limitation, please refer to this [bug](https://github.com/facebookresearch/fairseq/issues/5012).
|
||||
|
||||
```bash
|
||||
python --version # 3.8 <= Python < 3.11
|
||||
```
|
||||
|
||||
### Linux/MacOS 一键依赖安装启动脚本
|
||||
执行项目根目录下`run.sh`即可一键配置`venv`虚拟环境、自动安装所需依赖并启动主程序。
|
||||
### Linux/MacOS One-click Dependency Installation & Startup Script
|
||||
By executing `run.sh` in the project root directory, you can configure the `venv` virtual environment, automatically install the required dependencies, and start the main program with one click.
|
||||
```bash
|
||||
sh ./run.sh
|
||||
```
|
||||
|
||||
### 手动安装依赖
|
||||
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/
|
||||
### Manual Installation of Dependencies
|
||||
1. Install `pytorch` and its core dependencies, skip if already installed. Refer to: https://pytorch.org/get-started/locally/
|
||||
```bash
|
||||
pip install torch torchvision torchaudio
|
||||
```
|
||||
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
|
||||
2. If you are using Nvidia Ampere architecture (RTX30xx) in Windows, according to the experience of #21, you need to specify the cuda version corresponding to pytorch.
|
||||
```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
|
||||
3. Install the corresponding dependencies according to your own graphics card.
|
||||
- Nvidia GPU
|
||||
```bash
|
||||
pip install -r requirements/main.txt
|
||||
```
|
||||
- A卡/I卡
|
||||
- AMD/Intel GPU
|
||||
```bash
|
||||
pip install -r requirements/dml.txt
|
||||
```
|
||||
- A卡ROCM(Linux)
|
||||
- AMD ROCM (Linux)
|
||||
```bash
|
||||
pip install -r requirements/amd.txt
|
||||
```
|
||||
- I卡IPEX(Linux)
|
||||
- Intel IPEX (Linux)
|
||||
```bash
|
||||
pip install -r requirements/ipex.txt
|
||||
```
|
||||
|
||||
## 其他资源准备
|
||||
### 1. assets
|
||||
> RVC需要位于`assets`文件夹下的一些模型资源进行推理和训练。
|
||||
#### 自动检查/下载资源(默认)
|
||||
> 默认情况下，RVC可在主程序启动时自动检查所需资源的完整性。
|
||||
## Preparation of Other Files
|
||||
### 1. Assets
|
||||
> RVC requires some models located in the `assets` folder for inference and training.
|
||||
#### Check/Download Automatically (Default)
|
||||
> By default, RVC can automatically check the integrity of the required resources when the main program starts.
|
||||
|
||||
> 即使资源不完整，程序也将继续启动。
|
||||
> Even if the resources are not complete, the program will continue to start.
|
||||
|
||||
- 如果您希望下载所有资源，请添加`--update`参数
|
||||
- 如果您希望跳过启动时的资源完整性检查，请添加`--nocheck`参数
|
||||
- If you want to download all resources, please add the `--update` parameter.
|
||||
- If you want to skip the resource integrity check at startup, please add the `--nocheck` parameter.
|
||||
|
||||
#### 手动下载资源
|
||||
> 所有资源文件均位于[Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
|
||||
#### Download Manually
|
||||
> All resource files are located in [Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
|
||||
|
||||
> 你可以在`tools`文件夹找到下载它们的脚本
|
||||
> You can find some scripts to download them in the `tools` folder
|
||||
|
||||
> 你也可以使用模型/整合包/工具的一键下载器：[RVC-Models-Downloader](https://github.com/fumiama/RVC-Models-Downloader)
|
||||
> You can also use the [one-click downloader](https://github.com/fumiama/RVC-Models-Downloader) for models/integration packages/tools
|
||||
|
||||
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。
|
||||
Below is a list that includes the names of all pre-models and other files required by RVC.
|
||||
|
||||
- ./assets/hubert/hubert_base.pt
|
||||
```bash
|
||||
@@ -119,90 +121,88 @@ sh ./run.sh
|
||||
```bash
|
||||
rvcmd assets/uvr5 # RVC-Models-Downloader command
|
||||
```
|
||||
想使用v2版本模型的话，需要额外下载
|
||||
If you want to use the v2 version of the model, you need to download additional resources in
|
||||
|
||||
- ./assets/pretrained_v2
|
||||
```bash
|
||||
rvcmd assets/v2 # RVC-Models-Downloader command
|
||||
```
|
||||
|
||||
### 2. 安装 ffmpeg 工具
|
||||
若已安装`ffmpeg`和`ffprobe`则可跳过此步骤。
|
||||
|
||||
#### Ubuntu/Debian 用户
|
||||
### 2. Install ffmpeg tool
|
||||
If `ffmpeg` and `ffprobe` have already been installed, you can skip this step.
|
||||
#### Ubuntu/Debian
|
||||
```bash
|
||||
sudo apt install ffmpeg
|
||||
```
|
||||
#### MacOS 用户
|
||||
#### MacOS
|
||||
```bash
|
||||
brew install ffmpeg
|
||||
```
|
||||
#### Windows 用户
|
||||
下载后放置在根目录。
|
||||
#### Windows
|
||||
After downloading, place it in the root directory.
|
||||
```bash
|
||||
rvcmd tools/ffmpeg # RVC-Models-Downloader command
|
||||
```
|
||||
- 下载[ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe)
|
||||
- [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe)
|
||||
|
||||
- 下载[ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe)
|
||||
- [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe)
|
||||
|
||||
### 3. 下载 rmvpe 人声音高提取算法所需文件
|
||||
### 3. Download the required files for the rmvpe vocal pitch extraction algorithm
|
||||
|
||||
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`assets/rmvpe`。
|
||||
If you want to use the latest RMVPE vocal pitch extraction algorithm, you need to download the pitch extraction model parameters and place them in `assets/rmvpe`.
|
||||
|
||||
- 下载[rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
|
||||
- [rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)
|
||||
```bash
|
||||
rvcmd assets/rmvpe # RVC-Models-Downloader command
|
||||
```
|
||||
|
||||
#### 下载 rmvpe 的 dml 环境(可选, A卡/I卡用户)
|
||||
#### Download DML environment of RMVPE (optional, for AMD/Intel GPU)
|
||||
|
||||
- 下载[rmvpe.onnx](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx)
|
||||
- [rmvpe.onnx](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx)
|
||||
```bash
|
||||
rvcmd assets/rmvpe # RVC-Models-Downloader command
|
||||
```
|
||||
|
||||
### 4. AMD显卡Rocm(可选, 仅Linux)
|
||||
### 4. AMD ROCM (optional, Linux only)
|
||||
|
||||
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。
|
||||
If you want to run RVC on a Linux system based on AMD's ROCM technology, please first install the required drivers [here](https://rocm.docs.amd.com/en/latest/deploy/linux/os-native/install.html).
|
||||
|
||||
若你使用的是Arch Linux，可以使用pacman来安装所需驱动：
|
||||
If you are using Arch Linux, you can use pacman to install the required drivers.
|
||||
````
|
||||
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）：
|
||||
For some models of graphics cards, you may need to configure the following environment variables (such as: 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：
|
||||
Also, make sure your current user is in the `render` and `video` user groups.
|
||||
````
|
||||
sudo usermod -aG render $USERNAME
|
||||
sudo usermod -aG video $USERNAME
|
||||
````
|
||||
|
||||
## 开始使用
|
||||
### 直接启动
|
||||
使用以下指令来启动 WebUI
|
||||
## Getting Started
|
||||
### Direct Launch
|
||||
Use the following command to start the WebUI.
|
||||
```bash
|
||||
python web.py
|
||||
```
|
||||
### Linux/MacOS 用户
|
||||
### Linux/MacOS
|
||||
```bash
|
||||
./run.sh
|
||||
```
|
||||
### 对于需要使用IPEX技术的I卡用户(仅Linux)
|
||||
### For I-card users who need to use IPEX technology (Linux only)
|
||||
```bash
|
||||
source /opt/intel/oneapi/setvars.sh
|
||||
./run.sh
|
||||
```
|
||||
### 使用整合包 (Windows 用户)
|
||||
下载并解压`RVC-beta.7z`，解压后双击`go-web.bat`即可一键启动。
|
||||
### Using the Integration Package (Windows Users)
|
||||
Download and unzip `RVC-beta.7z`. After unzipping, double-click `go-web.bat` to start the program with one click.
|
||||
```bash
|
||||
rvcmd packs/general/latest # RVC-Models-Downloader command
|
||||
```
|
||||
|
||||
## 参考项目
|
||||
## Credits
|
||||
+ [ContentVec](https://github.com/auspicious3000/contentvec/)
|
||||
+ [VITS](https://github.com/jaywalnut310/vits)
|
||||
+ [HIFIGAN](https://github.com/jik876/hifi-gan)
|
||||
@@ -213,5 +213,5 @@ rvcmd packs/general/latest # RVC-Models-Downloader command
|
||||
+ [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).
|
||||
|
||||
## 感谢所有贡献者作出的努力
|
||||
## Thanks to all contributors for their efforts
|
||||
[](https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI/graphs/contributors)
|
||||
|
||||
Reference in New Issue
Block a user