rvc-model

weizuo/rvc-model

Publisherweizuo

Download access requirementsModelScope source

Retrieval-based-Voice-Conversion-WebUI 一个基于VITS的简单易用的变声框架 [](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)

Speech & Audio

View all download instructions Mirror repository documentation and license ↗

Model details

模型介绍

中文整理

Retrieval-based-Voice-Conversion-WebUI

一个基于VITS的简单易用的变声框架

[](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)

[](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval based Voice Conversion WebUI.ipynb)

[](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/LICENSE)

[](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)

[](https://discord.gg/HcsmBBGyVk)

更新日志** **常见问题解答** **AutoDL·5毛钱训练AI歌手** **对照实验记录**) **在线演示**

English** **中文简体** **日本語** **한국어** (**韓國語**) **Français** **Türkçe** **Português**

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

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。

训练推理界面

实时变声界面

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。

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

点此查看我们的演示视频 !

环境配置

以下指令需在 Python 版本大于3.8的环境中执行。

ModelScope使用方法

Notebook快速开发启动后，把项目根目录下的rvc.ipynb文件上传到notebook开发界面目录下，然后点开文件，一键运行就是了（notebook实例环境需要有GPU才可正常运行）

Windows/Linux/MacOS等平台通用方法

下列方法任选其一。

通过 pip 安装依赖
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/

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

根据自己的显卡安装对应依赖

N卡

A卡/I卡

A卡ROCM(Linux)

I卡IPEX(Linux)

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

通过 Poetry 安装依赖时，python 建议使用 3.7-3.10 版本，其余版本在安装 llvmlite==0.39.0 时会出现冲突

MacOS

可以通过 run.sh 来安装依赖

安装 ffmpeg

Ubuntu/Debian 用户

MacOS 用户

Windows 用户

下载后放置在根目录。

下载ffmpeg.exe

下载ffprobe.exe

开始使用

直接启动

使用以下指令来启动 WebUI

若先前使用 Poetry 安装依赖，则可以通过以下方式启动WebUI

使用整合包

下载并解压 RVC-beta.7z

Windows 用户

双击 go-web.bat

MacOS 用户

对于需要使用IPEX技术的I卡用户(仅Linux)

参考项目

ContentVec

VITS

HIFIGAN

Gradio

FFmpeg

Ultimate Vocal Remover

audio-slicer

Vocal pitch extraction:RMVPE

+ The pretrained model is trained and tested by yxlllc and RVC-Boss.

感谢所有贡献者作出的努力

优先采用原作者提供的中文模型卡片；仅有英文说明时由闲社AI翻译整理。重要参数、许可证和商用范围请以原文为准。

你将获得什么

完整仓库方式包含该固定版本中的权重、配置、分词器及说明文件；指定版本方式只下载所选文件或整组分片。多模态模型的投影文件、配置等依赖，请按作者说明配齐。

完整仓库可能包含多个权重格式，因此需要的磁盘空间可能大于单一格式的模型大小。下载文件不等于完成模型部署。

使用前须知

运行环境

运行模型需要的设备、工具与依赖，以原作者说明为准。

授权范围

是否允许商用、修改和分发，请查看模型许可证。

闲社提供资料与镜像下载方法，不代表已运行模型或完成安全审计。下载的代码应先检查，再执行。

Problem with the information or download?

Pinned version · Multiple download options

rvc-model model download

Download the full repository or choose a version or file.

许可待确认

下载入口不代表获得修改、分发或商用授权。使用前请查阅原仓库说明、LICENSE 或联系作者确认；闲社未验证模型运行效果。

查看原作者说明与许可 →

Download tools · More than GGUF

Use the Hugging Face download tool to obtain weizuo/rvc-model. Download Safetensors, GGUF, ONNX, configuration and other repository files. Downloading does not mean the tool can run this model.

Pinned-version file information is being completed. Existing downloads remain available, or load the file manifest below.

Choose a mirror or official source, your operating system and download scope below, then copy the command. Install the download tool first if needed.

Pinned version: c1c10edefe2a5ea54f6454a038600c271c59407d. Downloads files only; does not start the model.

Choose a download source

Pinned ModelScope version: c1c10edefe2a5ea54f6454a038600c271c59407d. Version identifiers can differ across sites. The alternative source was provided after checking weights and runtime configuration; this is not proof of a successful model run.

A checked, pinned ModelScope source is available for this model. Use the ModelScope download tool.

Choose what to download

Need just one GGUF precision? Load the file manifest and choose a version. Direct file links do not require Python; the command below can download multiple shards together.

Quantization / file

This reads the pinned version's file manifest; no model weights are downloaded.

Choose your operating system

For command-line downloads, follow these steps to get the full repository or selected files. Direct file links do not need these steps.

Open a terminal window

Create and open a folder for the model. In the folder's address bar, enter powershell and press Enter.

If Python is not installed, get it from the official Python website. In the terminal, enter python --version; continue when a version number appears.

First time? Install the download tool

Copy this command, paste it into the terminal, press Enter and wait for installation to finish.

python -m pip install --upgrade huggingface_hub

Already installed? Continue to step 3.

Run the download command

Select the button below, paste into the same terminal and press Enter. The tool downloads all files included in the current command.

Copying does not start a download. Paste and run the command on your device.

Where are the downloaded files?

Open the folder you chose. Look for the models folder. When progress stops and the terminal returns to its prompt without errors, check that all files are present. 'Copied' does not mean 'downloaded'.

No response or an error?

python not found: Install Python and reopen the terminal. On Windows, follow the installer's instructions to enable command-line access.

hf not found: Confirm that step 2 succeeded, then reopen the terminal. If needed, add Python's Scripts folder to your user PATH. Do not repeatedly download scripts.

Network interrupted: Stay in the same folder and run the same command again. The tool checks existing files.

Permission or disk error: Choose a writable folder with enough free space. Do not disable system security protection.

View the full download command

modelscope download --model "weizuo/rvc-model" --revision "c1c10edefe2a5ea54f6454a038600c271c59407d" --local_dir "./models/weizuo--rvc-model--ms-c1c10edefe2a"

Files transfer directly from the source you choose, not through Xianshe servers.

The version is pinned. Repeating the same command checks existing files. Change the source manually if it is slow or unavailable.

Public models do not require submitting keys to Xianshe. Restricted models still require the author's authorization. On Linux / macOS, use python3 instead of python when appropriate.