Fixed tokenizer and audio processing logic #214
Conversation
This file contains 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
1amageek
commented
Oct 3, 2024
| @@ -22,16 +22,14 @@ public class AudioEncoder: AudioEncoding, WhisperMLModel { | |||
| guard let inputDescription = model?.modelDescription.outputDescriptionsByName["encoder_output_embeds"] else { return nil } | |||
| guard inputDescription.type == .multiArray else { return nil } | |||
| guard let shapeConstraint = inputDescription.multiArrayConstraint else { return nil } | |||
| let shape = shapeConstraint.shape.map { $0.intValue } | |||
| return shape[1] | |||
| return shapeConstraint.shape[0].intValue | |||
There was a problem hiding this comment.
shape[0]: Batch size
shape[1]: Sequence length
shape[2]: Embedding dimension
There was a problem hiding this comment.
|
Hi @1amageek, I'm happy to see your enthusiasm to contribute to WhisperKit! I'd like to make a few recommendations to help guide your work in the future, since this PR has grown quite large.
With this in mind, I would recommend closing this PR and separating out the changes that add new features or fix existing bugs into separate PRs with details on why they are necessary and solve an open issue listed in https://github.com/argmaxinc/WhisperKit/issues. Thanks again for your contributions so far, open to any discussion on these topics. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This PR addresses the following changes:
WhisperTokenizerWrapper.startIndexvalidation inAudioChunker.swiftandAudioProcessor.swift.embedSizeandsequenceLengthcalculations inAudioEncoder.swift.applyChatTemplateandencodemethods.Package.swift.