Fix Moonshine ASR token decoding - #1738
Open
Mr-Neutr0n wants to merge 1 commit into
Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Fixes Moonshine automatic speech recognition pipelines that fail during token decoding.
Moonshine processors can contain only a feature extractor, while the tokenizer is loaded separately on the pipeline.
_call_moonshinecurrently asks the processor to decode generated token IDs, which raisesUnable to decode without a tokenizer. This change uses the pipeline tokenizer, matching the other ASR paths.The regression test constructs a processor without a tokenizer and verifies that generated tokens are decoded through the pipeline tokenizer.
Fixes #1735.
Tests
pnpm buildpasses, including TypeScript type generation