{"id":13545190,"url":"https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI","last_synced_at":"2025-04-02T15:31:01.340Z","repository":{"id":149813777,"uuid":"619521008","full_name":"RVC-Project/Retrieval-based-Voice-Conversion-WebUI","owner":"RVC-Project","description":"Easily train a good VC model with voice data \u003c= 10 mins!","archived":false,"fork":false,"pushed_at":"2024-11-24T15:09:44.000Z","size":14585,"stargazers_count":28260,"open_issues_count":541,"forks_count":3996,"subscribers_count":191,"default_branch":"main","last_synced_at":"2025-03-30T00:02:18.206Z","etag":null,"topics":["audio-analysis","change","conversational-ai","conversion","converter","retrieval-model","retrieve-data","rvc","so-vits-svc","sovits","vc","vits","voice","voice-conversion","voice-converter","voiceconversion"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/RVC-Project.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-03-27T09:59:10.000Z","updated_at":"2025-03-29T23:45:47.000Z","dependencies_parsed_at":"2024-04-19T16:03:47.700Z","dependency_job_id":"5155c229-f7fb-4fa5-864d-ab10f0ffacd5","html_url":"https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI","commit_stats":null,"previous_names":[],"tags_count":14,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RVC-Project%2FRetrieval-based-Voice-Conversion-WebUI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RVC-Project%2FRetrieval-based-Voice-Conversion-WebUI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RVC-Project%2FRetrieval-based-Voice-Conversion-WebUI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RVC-Project%2FRetrieval-based-Voice-Conversion-WebUI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RVC-Project","download_url":"https://codeload.github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246841611,"owners_count":20842620,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["audio-analysis","change","conversational-ai","conversion","converter","retrieval-model","retrieve-data","rvc","so-vits-svc","sovits","vc","vits","voice","voice-conversion","voice-converter","voiceconversion"],"created_at":"2024-08-01T11:00:58.803Z","updated_at":"2025-04-02T15:30:59.694Z","avatar_url":"https://github.com/RVC-Project.png","language":"Python","readme":"\u003cdiv align=\"center\"\u003e\n\n\u003ch1\u003eRetrieval-based-Voice-Conversion-WebUI\u003c/h1\u003e\n一个基于VITS的简单易用的变声框架\u003cbr\u003e\u003cbr\u003e\n\n[![madewithlove](https://img.shields.io/badge/made_with-%E2%9D%A4-red?style=for-the-badge\u0026labelColor=orange\n)](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)\n\n\u003cimg src=\"https://counter.seku.su/cmoe?name=rvc\u0026theme=r34\" /\u003e\u003cbr\u003e\n\n[![Open In Colab](https://img.shields.io/badge/Colab-F9AB00?style=for-the-badge\u0026logo=googlecolab\u0026color=525252)](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)\n[![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)\n[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)\n\n[![Discord](https://img.shields.io/badge/RVC%20Developers-Discord-7289DA?style=for-the-badge\u0026logo=discord\u0026logoColor=white)](https://discord.gg/HcsmBBGyVk)\n\n[**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)\n\n[**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)\n\n\u003c/div\u003e\n\n\u003e 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\n\n\u003e 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。\n\n\u003ctable\u003e\n   \u003ctr\u003e\n\t\t\u003ctd align=\"center\"\u003e训练推理界面\u003c/td\u003e\n\t\t\u003ctd align=\"center\"\u003e实时变声界面\u003c/td\u003e\n\t\u003c/tr\u003e\n  \u003ctr\u003e\n\t\t\u003ctd align=\"center\"\u003e\u003cimg src=\"https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/assets/129054828/092e5c12-0d49-4168-a590-0b0ef6a4f630\"\u003e\u003c/td\u003e\n    \u003ctd align=\"center\"\u003e\u003cimg src=\"https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/assets/129054828/730b4114-8805-44a1-ab1a-04668f3c30a6\"\u003e\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t\t\u003ctd align=\"center\"\u003ego-web.bat\u003c/td\u003e\n\t\t\u003ctd align=\"center\"\u003ego-realtime-gui.bat\u003c/td\u003e\n\t\u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd align=\"center\"\u003e可以自由选择想要执行的操作。\u003c/td\u003e\n\t\t\u003ctd align=\"center\"\u003e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。\u003c/td\u003e\n\t\u003c/tr\u003e\n\u003c/table\u003e\n\n## 简介\n本仓库具有以下特点\n+ 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\n+ 即便在相对较差的显卡上也能快速训练\n+ 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)\n+ 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)\n+ 简单易用的网页界面\n+ 可调用UVR5模型来快速分离人声和伴奏\n+ 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\n+ A卡I卡加速支持\n\n点此查看我们的[演示视频](https://www.bilibili.com/video/BV1pm4y1z7Gm/) !\n\n## 环境配置\n以下指令需在 Python 版本大于3.8的环境中执行。  \n\n### Windows/Linux/MacOS等平台通用方法\n下列方法任选其一。\n#### 1. 通过 pip 安装依赖\n1. 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/\n```bash\npip install torch torchvision torchaudio\n```\n2. 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\n```bash\npip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117\n```\n3. 根据自己的显卡安装对应依赖\n- N卡\n```bash\npip install -r requirements.txt\n```\n- A卡/I卡\n```bash\npip install -r requirements-dml.txt\n```\n- A卡ROCM(Linux)\n```bash\npip install -r requirements-amd.txt\n```\n- I卡IPEX(Linux)\n```bash\npip install -r requirements-ipex.txt\n```\n\n#### 2. 通过 poetry 来安装依赖\n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\n```bash\ncurl -sSL https://install.python-poetry.org | python3 -\n```\n\n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\n```bash\npoetry init -n\npoetry env use \"path to your python.exe\"\npoetry run pip install -r requirments.txt\n```\n\n### MacOS\n可以通过 `run.sh` 来安装依赖\n```bash\nsh ./run.sh\n```\n\n## 其他预模型准备\nRVC需要其他一些预模型来推理和训练。\n\n你可以从我们的[Hugging Face space](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)下载到这些模型。\n\n### 1. 下载 assets\n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。\n\n- ./assets/hubert/hubert_base.pt\n\n- ./assets/pretrained \n\n- ./assets/uvr5_weights\n\n想使用v2版本模型的话，需要额外下载\n\n- ./assets/pretrained_v2\n\n### 2. 安装 ffmpeg\n若ffmpeg和ffprobe已安装则跳过。\n\n#### Ubuntu/Debian 用户\n```bash\nsudo apt install ffmpeg\n```\n#### MacOS 用户\n```bash\nbrew install ffmpeg\n```\n#### Windows 用户\n下载后放置在根目录。\n- 下载[ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe)\n\n- 下载[ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe)\n\n### 3. 下载 rmvpe 人声音高提取算法所需文件\n\n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。\n\n- 下载[rmvpe.pt](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.pt)\n\n#### 下载 rmvpe 的 dml 环境(可选, A卡/I卡用户)\n\n- 下载[rmvpe.onnx](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/rmvpe.onnx)\n\n### 4. AMD显卡Rocm(可选, 仅Linux)\n\n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。\n\n若你使用的是Arch Linux，可以使用pacman来安装所需驱动：\n````\npacman -S rocm-hip-sdk rocm-opencl-sdk\n````\n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）：\n````\nexport ROCM_PATH=/opt/rocm\nexport HSA_OVERRIDE_GFX_VERSION=10.3.0\n````\n同时确保你的当前用户处于`render`与`video`用户组内：\n````\nsudo usermod -aG render $USERNAME\nsudo usermod -aG video $USERNAME\n````\n\n## 开始使用\n### 直接启动\n使用以下指令来启动 WebUI\n```bash\npython infer-web.py\n```\n\n若先前使用 Poetry 安装依赖，则可以通过以下方式启动WebUI\n```bash\npoetry run python infer-web.py\n```\n\n### 使用整合包\n下载并解压`RVC-beta.7z`\n#### Windows 用户\n双击`go-web.bat`\n#### MacOS 用户\n```bash\nsh ./run.sh\n```\n### 对于需要使用IPEX技术的I卡用户(仅Linux)\n```bash\nsource /opt/intel/oneapi/setvars.sh\n```\n\n## 参考项目\n+ [ContentVec](https://github.com/auspicious3000/contentvec/)\n+ [VITS](https://github.com/jaywalnut310/vits)\n+ [HIFIGAN](https://github.com/jik876/hifi-gan)\n+ [Gradio](https://github.com/gradio-app/gradio)\n+ [FFmpeg](https://github.com/FFmpeg/FFmpeg)\n+ [Ultimate Vocal Remover](https://github.com/Anjok07/ultimatevocalremovergui)\n+ [audio-slicer](https://github.com/openvpi/audio-slicer)\n+ [Vocal pitch extraction:RMVPE](https://github.com/Dream-High/RMVPE)\n  + The pretrained model is trained and tested by [yxlllc](https://github.com/yxlllc/RMVPE) and [RVC-Boss](https://github.com/RVC-Boss).\n\n## 感谢所有贡献者作出的努力\n\u003ca href=\"https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/graphs/contributors\" target=\"_blank\"\u003e\n  \u003cimg src=\"https://contrib.rocks/image?repo=RVC-Project/Retrieval-based-Voice-Conversion-WebUI\" /\u003e\n\u003c/a\u003e\n","funding_links":[],"categories":["Python","Deep Voice (Text to Speech \u0026 Speech to Speech)","语音合成","Voice Cloning \u0026 Conversion","Repos","Multimodal","Voice \u0026 Multimodal (local) (16)"],"sub_categories":["Prompt Generator","网络服务_其他","Voice Conversion (STS)","1. Audio"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRVC-Project%2FRetrieval-based-Voice-Conversion-WebUI","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FRVC-Project%2FRetrieval-based-Voice-Conversion-WebUI","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRVC-Project%2FRetrieval-based-Voice-Conversion-WebUI/lists"}