Closed 980202006 closed 1 year ago
Good Work!I want to train speaker embedding on my own data set, is there any relevant code or paper?
https://github.com/mozilla/TTS/tree/master/TTS/speaker_encoder
Thank you!
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。
Good Work!I want to train speaker embedding on my own data set, is there any relevant code or paper?