Use model.safetensors with Whisper#1399
Merged
awni merged 1 commit intoml-explore:mainfrom Dec 15, 2025
Merged
Conversation
awni
approved these changes
Dec 14, 2025
|
What is the release policy here? The latest version on PyPI is still 0.4.3 (released Aug 29, 2025). These changes aren’t included in the current mlx-whisper Python package, which is confusing when trying conversion for the first time. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
I've created new Whisper repos on Hugging Face with the weights stored in
model.safetensorsfiles for use with my Swift port of Whisper in mlx-swift-audio. Many of the Whisper models in the MLX Community include the weights in .npz format, which Swift apps can't read. OpenAI's Whisper repos on Hugging Face usemodel.safetensors.I've updated the model loading logic to look for
model.safetensorsfirst and fall back toweights.safetensorsandweights.npz. The conversion script now saves the weights asmodel.safetensors.