feat(stt): add support for MedASR (Lasr architecture) #376
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
added 3 commits
January 15, 2026 17:57
This commit adds full support for the MedASR model (Lasr architecture) to mlx-audio. Changes: - Added implementation (LasrEncoder, LasrForCTC). - Updated and to support model type. - Fixed model loading logic in to correctly handle mapped model types. - Added for weight conversion from Hugging Face. - Added examples: - : File-based transcription. - : Live transcription with TEN-VAD and ring buffer.
Blaizzy
requested changes
Jan 16, 2026
Contributor
Author
|
Thanks for the feedback, King! The torch and mps in the example scripts was to roughly compare the speed gain with mlx; I've removed them from the example scripts. |
Contributor
Author
|
I removed another unnecessary file and recommitted. Sorry for the mess. |
Blaizzy
requested changes
Jan 22, 2026
Blaizzy
requested changes
Jan 25, 2026
linejunkie171-lab
approved these changes
Jan 25, 2026
added 6 commits
January 26, 2026 08:54
Blaizzy
reviewed
Jan 26, 2026
Blaizzy
reviewed
Jan 26, 2026
Blaizzy
reviewed
Jan 26, 2026
Blaizzy
reviewed
Jan 26, 2026
Blaizzy
requested changes
Jan 26, 2026
Owner
Blaizzy
left a comment
Blaizzy
left a comment
There was a problem hiding this comment.
Almost there. A few final nits and we are ready to merge.
…e method, update example
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
WARNING! This is my first PR sorry if it's crappy.
I've gotta come clean here; Antigravity did everything, but I made sure it works !
This PR adds support for Google's MedASR model (Lasr architecture).
Changes:
mlx_audio/stt/models/lasr/implementation (LasrEncoder, LasrForCTC).utils.pyto supportlasr_ctcmodel type.utils.py: Added fallback to mapped model type inget_model_classto correctly resolvelasr_ctc->lasrwhen model name doesn't match a directory.examples/medasr_transcribe.py.Verification:
google/medasr.