vits icon indicating copy to clipboard operation
vits copied to clipboard

Can you provide typical loss figures ? KL diverging

Open godefv opened this issue 4 years ago • 0 comments

Hello,

I am training from scratch using custom data. The Hifi-GAN part has converged relatively quickly, and the generated samples in the evaluation tensorboard sound really good.

However, the inference samples from phonemes don't seem to improve. Moreover, The kl-loss, which, as I understand, should be the next loss to converge, is rather diverging.

Here are my generator losses : 2021-07-15-093309_1015x561_scrot

The jump is because the training was interrupted and the step number is wrong when loading from a checkpoint.

So, is this normal ? Do you have typical loss figures to share to compare with ? Thanks.

godefv avatar Jul 15 '21 07:07 godefv