prevent double-encoding of captions for audio auto-split dataset #2543
Conversation
This file contains hidden or 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
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Outdated suggestions cannot be applied.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.
This pull request introduces a safeguard to the text embeddings processing logic for audio datasets that source their data from video. Specifically, it ensures that text embedding processing is skipped for these datasets, as they inherit captions from their parent video dataset during training.
Text embedding processing logic:
simpletuner/helpers/data_backend/factory.py, the_process_text_embeddingsfunction now checks if the audio dataset is configured withsource_from_video=Trueand skips text embedding processing in that case, logging an informational message. This prevents redundant processing since captions are inherited from the parent dataset.