Open thunn opened 1 month ago
Hi,
Have you listened to the synthesized samples?
The duration loss can increase at the validation phase.
Although the diffusion loss does not improve a lot in training phase, more steps usually guarantee better sample quality as in Grad-TTS.
Thanks.
Hello,
I recently ran the GeDEX-TTS training using the VCTK dataset and followed the instructions provided in the GeDEX-TTS/config/VCTK/base.yaml configuration file. The only modifications I made were:
vocoder
tobigvgan
vocoder path
tobigvgan/bigvgan_22khz_80band
While plotting the training logs, I observed that the model started to overfit very early in the training process. This is somewhat unexpected to me, and I wanted to inquire whether this behaviour is expected or if there might be an issue with my setup.
Here is a basic plot of the training losses.
Could you please provide insights into whether early overfitting is a known issue with this configuration, or if there are any recommended adjustments to prevent this?
Thank you for your help!