search

PlayVoice / whisper-vits-svc

Core Engine of Singing Voice Conversion & Singing Voice Clone
https://huggingface.co/spaces/maxmax20160403/sovits5.0
MIT License
2.6k stars 919 forks source link

Ask for training method about speaker embedding #66

Closed 980202006 closed 1 year ago

980202006 commented 1 year ago

Good Work!I want to train speaker embedding on my own data set, is there any relevant code or paper?

MaxMax2016 commented 1 year ago

https://github.com/mozilla/TTS/tree/master/TTS/speaker_encoder

980202006 commented 1 year ago

Thank you!

zdj97 commented 6 months ago

这个是说话人识别模型嘛 看他github里介绍的不多。换成其他声纹模型可行吗

MaxMax2016 commented 6 months ago

这个是说话人识别模型嘛 看他github里介绍的不多。换成其他声纹模型可行吗

从头训练模型的话，换成其他声纹模型是可行的；微调SVC模型的话，换成其他声纹模型，收敛速度可能不是那么好。