GitHub 热门项目:GPT-SoVITS

摘要

GitHub项目:GPT-SoVITS 仓库地址:https://github。com/RVC-Boss/GPT-SoVITS Stars:57370 | 作者:RVC-Boss 项目描述:1 min voice data can also be used to train a good TTS model。

https badge the for img
2026-05-11 1 阅读 GitHub Trending
GitHub 项目:GPT-SoVITS 仓库地址:https://github.com/RVC-Boss/GPT-SoVITS 星级:57370 | 作者:RVC-Boss 项目描述:1分钟语音数据也可以用来训练一个好的TTS模型! (几张声音克隆镜头) =================================================== 自述文件内容:

GPT-SoVITS-WebUI

强大的少量语音转换和文本到语音 WebUI。

[![madewithlove](https://img.shields.io/badge/made_with-%E2%9D%A4-red?style=for-the-badge&labelColor=orange)](https://github.com/RVC-Boss/GPT-SoVITS) RVC-Boss%2FGPT-SoVITS | Trendshift [![Python](https://img.shields.io/badge/python-3.10--3.12-blue?style=for-the-badge&logo=python)](https://www.python.org) [![GitHub 发布](https://img.shields.io/github/v/release/RVC-Boss/gpt-sovits?style=for-the-badge&logo=github)](https://github.com/RVC-Boss/gpt-sovits/releases) [![在 Colab 中训练](https://img.shields.io/badge/Colab-Training-F9AB00?style=for-the-badge&logo=googlecolab)](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-WebUI.ipynb) [![Huggingface](https://img.shields.io/badge/免费在线体验-free_online_demo-yellow.svg?style=for-the-badge&logo=huggingface)](https://lj1995-gpt-sovits-proplus.hf.space/) [![图像大小](https://img.shields.io/docker/image-size/xxxxrt666/gpt-sovits/latest?style=for-the-badge&logo=docker)](https://hub.docker.com/r/xxxxrt666/gpt-sovits) [![简体中文](https://img.shields.io/badge/简体中文-阅读文档-blue?style=for-the-badge&logo=googledocs&logoColor=white)](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e) [![英语](https://img.shields.io/badge/English-Read%20Docs-blue?style=for-the-badge&logo=googledocs&logoColor=white)](https://rentry.co/GPT-SoVITS-guide#/) [![更改日志](https://img.shields.io/badge/Change%20Log-View%20Updates-blue?style=for-the-badge&logo=googledocs&logoColor=white)](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/docs/en/Changelog_EN.md) [![许可证](https://img.shields.io/badge/LICENSE-MIT-green.svg?style=for-the-badge&logo=opensourceinitiative)](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE) **英语** | [**中文简体**](./docs/cn/README.md) | [**日本语**](./docs/ja/README.md) | [**한국어**](./docs/ko/README.md) | [**土耳其**](./docs/tr/README.md)
--- ## 特点: 1. **零镜头 TTS:** 输入 5 秒的声音样本,体验即时文本到语音的转换。 2. **少量 TTS:** 只需 1 分钟的训练数据即可微调模型,以提高语音相似度和真实度。 3. **跨语言支持:** 使用与训练数据集不同的语言进行推理,目前支持英语、日语、韩语、粤语和中文。 4. **WebUI工具:** 集成工具包括语音伴奏分离、自动训练集分割、中文ASR和文本标注,帮助初学者创建训练数据集和GPT/SoVITS模型。 **在这里查看我们的[演示视频](https://www.bilibili.com/video/BV12g4y1m7Uw)!** 看不见的扬声器少量微调