Implement whisper_token_to_bytes#148
Merged
absadiki merged 1 commit intoabsadiki:mainfrom Dec 20, 2025
Merged
Conversation
Not every token seems to be valid unicode but every token is interpreted as such in `pw.whisper_token_to_str`. While this can be caught with an exception handler it might be worthwhile to have a way of getting the token bytes instead and parsing them using `.decode`, e.g.: ```python str(pw.whisper_token_to_bytes(ctx, tid), 'utf8', 'ignore') ```
Owner
|
Thanks for pointing this out! Yes, We can definitely expose the raw token bytes, similar to how full_segment already works. |
Author
|
I'm not sure this is related to the PR. Can you restart the CI for these runs (it's only Windows). |
Owner
|
I reran the CI and this time all jobs passed, including Windows. Not sure what caused the earlier failures, but it looks good now. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Not every token seems to be valid unicode but every token is interpreted as such in
pw.whisper_token_to_str. While this can be caught with an exception handler it might be worthwhile to have a way of getting the token bytes instead and parsing them using.decode, e.g.: