Fix Wav2Vec2 word delimiter special token handling#46578
Open
nightcityblade wants to merge 1 commit into
Open
Conversation
Contributor
|
CI Dashboard: View test results in Grafana |
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: wav2vec2 |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #46552.\n\nThis keeps the Wav2Vec2 CTC word delimiter from being treated as removable special token by special-token-aware APIs, matching the decode path behavior.\n\nChanges:\n- Preserve the word delimiter in convert_ids_to_tokens(..., skip_special_tokens=True).\n- Exclude the word delimiter from get_special_tokens_mask(..., already_has_special_tokens=True).\n- Add a regression test for delimiter masking/skipping.\n\nTests:\n- python -m pytest tests/models/wav2vec2/test_tokenization_wav2vec2.py -q