search

yl4579 / StyleTTS

Official Implementation of StyleTTS
MIT License
387 stars 62 forks source link

about ASR model #43

Closed hdmjdp closed 1 year ago

hdmjdp commented 1 year ago

If we do not use pretrained ASR ckpt, just let the asr model update parameters according to TTS model. Can we get good TTS result?

yl4579 commented 1 year ago

Yes, but it would take more time, and you will need different learning rates for the TTS model and ASR model. See the hyperparameters of pre-training for the ASR model.