Description
利用OpenVPI开源团队改进的DiffSinger使用自制、有授权以及开源数据制作AI歌姬!
涵盖背景简介、数据准备、AI训练、演唱调教、AI伦理方面的讨论。
=======================================================
浙江大学DiffSinger项目:https://github.com/MoonInTheRiver/DiffSinger
OpenVPI DiffSinger项目:https://github.com/openvpi/DiffSinger
OpenVPI核心成员传送门:(包括但不限于)@孙飒_TS @YQ之神 @yxlllc 等
OpenVPI DiffSinger原始教程:https://www.yuque.com/openvpi/tutorial
OpenVPI DiffSinger 交流群:907879266
OpenSVIP工程转换器项目:https://openvpi.github.io
OpenVPI DiffSinger社区声码器企划:https://openvpi.github.io/vocoders/
OpenCPOP开源数据集:https://wenet.org.cn/opencpop/download/
M4Singer开源数据集:https://github.com/M4Singer/M4Singer
OpenAI Whisper: https://github.com/openai/whisper
OpenUTAU DiffSingerPack:https://github.com/xunmengshe/OpenUtau/releases
OpenUTAU 交流群:485658015
@Well404 的切分标注工具:https://github.com/Well2333/VoiceS
@冷月2333 音频预处理:https://github.com/fishaudio/audio-preprocess
@冷月2333 声码器增强:https://github.com/fishaudio/fish-diffusion