Ensures that only GPT model is in training mode during XTTS GPT training #3241
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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.