Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Ensures that only GPT model is in training mode during XTTS GPT training #3241

Merged
merged 2 commits into from
Nov 17, 2023

Conversation

Edresson
Copy link
Contributor

@Edresson Edresson commented Nov 16, 2023

Currently, during GPT XTTS training the DVAE are not in eval mode. This PR fixes it using the new on_train_epoch_start callback from the latest trainer version.

It also fix a issue with parallel wavegan unit test. The target_loss "loss_0" that is the default from GAN vocoder training do not exist for parallel wavegan and it raises an error with the latest trainer version.

@Edresson Edresson requested a review from erogol November 16, 2023 17:44
@erogol erogol merged commit 11283fc into dev Nov 17, 2023
53 checks passed
@erogol erogol deleted the xtts_gpt_eval_mode branch November 17, 2023 14:13
erogol pushed a commit that referenced this pull request Nov 17, 2023
…ing (#3241)

* Ensures that only GPT model is in training mode during training

* Fix parallel wavegan unit test
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants