Improve support for distil-large-v3 #1982
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
ggerganov
approved these changes
Mar 21, 2024
jiahansu
pushed a commit
to WiseSync/whisper.cpp
that referenced
this pull request
Apr 17, 2024
viktor-silakov
pushed a commit
to viktor-silakov/whisper_node_mic.cpp
that referenced
this pull request
May 11, 2024
iThalay
pushed a commit
to iThalay/whisper.cpp
that referenced
this pull request
Sep 23, 2024
iThalay
pushed a commit
to iThalay/whisper.cpp
that referenced
this pull request
Sep 23, 2024
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Outdated suggestions cannot be applied.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.
While the original Distil-Whisper models were trained on timestamps, they degraded significantly after 15-seconds of audio (due to the shorter distribution of audio we trained on). The implementation in Whisper cpp thus deactivated timestamps entirely for these checkpoints.
The latest Distil-Whisper release, distil-large-v3, addresses this problem, giving a model that accurately predicts timestamps in full 30-second windows, much like the original Whisper models.
To improve support for this new checkpoint, we allow timestamp prediction for the new checkpoint in this PR.