Fix Whisper export to support autoregressive decoding#34
Merged
carinapeng merged 2 commits intoJun 13, 2026
Conversation
stikves
approved these changes
Jun 13, 2026
stikves
pushed a commit
to stikves/coreai-models
that referenced
this pull request
Jun 13, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Purpose
The existing export traced decoder_input_ids at length 1 with no dynamic shapes, producing a model specialised to a single token. At inference time this means each decode step has no context — giving empty transcript
This fix adds dynamic_shapes for decoder_input_ids and traces with the 4-token forced prefix so torch.export generalises the sequence dimension to allow full autoregressive decoding.