Support distil whisper models #88
Merged
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
- Allows previous model download flows to continue working
ZachNagengast
commented
Mar 25, 2024
| @@ -57,7 +57,7 @@ struct ContentView: View { | |||
| @State private var currentFallbacks: Int = 0 | |||
| @State private var lastBufferSize: Int = 0 | |||
| @State private var lastConfirmedSegmentEndSeconds: Float = 0 | |||
| @State private var requiredSegmentsForConfirmation: Int = 2 | |||
| @State private var requiredSegmentsForConfirmation: Int = 4 | |||
There was a problem hiding this comment.
Updating this to account for #24 increasing the amount of segments generated overall
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Outdated suggestions cannot be applied.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.
Distil whisper models are a great addition to the standard openai models especially for smaller devices, and with distil large v3 out now, its a great time to add support for them.
Important note: This required some significant changes to how we search for models, specifically that we now require the full model name like "openai_whisper-large-v3" rather than just "large-v3" in order to use the convenience methods for downloading a model without doing it manually using the modelFolder param.
Swift
let pipe = try? await WhisperKit(model: "distil-whisper_distil-large-v3")or
let pipe = try? await WhisperKit(model: "distil*large-v3")CLI
swift run whisperkit-cli transcribe --model "large-v3" --model-prefix "distil" --audio-path ~/your-audio.mp3