Add large-v3-turbo to the Whisper model list - #47
Open
Suijiku wants to merge 1 commit into
Open
Conversation
faster-whisper already accepts the large-v3-turbo model; expose it in the Settings > Transcription combo and document it in the README models and settings tables. Turbo has 4 decoder layers vs large-v3's 32 (several times faster decode, ~0.3% WER difference).
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #44.
Summary
Adds
large-v3-turboto the Whisper model list in Settings → Transcription. faster-whisperalready accepts this model name; TalkTrack just didn't offer it in the UI.
large-v3-turbohas 4 decoder layers vslarge-v3's 32, giving several times faster decodefor roughly a ~0.3% WER difference — a strong default for users who want near-
large-v3accuracy without the full decode cost. First use downloads the model (~1.6 GB) and caches it
locally like the other models.
Changes
app/ui/settings_dialog.py— new combo item afterlarge-v3.README.md— new row in the Whisper Models table and updated Settings table.Testing
transcribed a short recording end-to-end.
~/.talktrack/settings.jsonand reloads).python -m pytest tests/ -v— full suite green.No behavior change for existing models; this is purely an added option.