glow-tts icon indicating copy to clipboard operation
glow-tts copied to clipboard

Published 20 hours ago • verified publisher icon jaywalnut310

Question about duration loss

Open Wangzhen-kris opened this issue 3 years ago • 1 comments

Hi, I trained the model with my own dataset. However, the duration loss increases gradually after a period of time for val data, it's overfitting, right? Can I stop the duration prediction after several epochs? image

Wangzhen-kris avatar May 26 '21 04:05 Wangzhen-kris

Yeah, also in my experience duration predictor usually overfits quite fast. However beware of your validation set, if you have any abruptly stopped sentences.

Adding onto this question; Did anyone experimented with replacing duration predictor with FastSpeech2's?

Selimonder avatar May 26 '21 08:05 Selimonder