feat: upgrade whisper model to large-v3-turbo #7

Merged
SaschaFuksa merged 2 commits from feat/large-v3-turbo into master 2026-04-18 16:01:40 +00:00
Owner

Switch from medium to large-v3-turbo whisper model for better transcription quality while maintaining reasonable speed.

Changes:

  • Dockerfile: download ggml-large-v3-turbo.bin instead of ggml-medium.bin
  • settings.yaml: model=large-v3-turbo
  • whisper_service.py: default model path updated
Switch from medium to large-v3-turbo whisper model for better transcription quality while maintaining reasonable speed. Changes: - Dockerfile: download ggml-large-v3-turbo.bin instead of ggml-medium.bin - settings.yaml: model=large-v3-turbo - whisper_service.py: default model path updated
large-v3-turbo delivers significantly better quality than medium while
being optimized for speed (turbo variant). Better transcription accuracy
with reasonable inference speed.
Merge remote-tracking branch 'origin/fix/last-chunk-not-sent'
Some checks are pending
CI / lint (pull_request) Waiting to run
CI / test (pull_request) Waiting to run
becd7e6a0b
SaschaFuksa deleted branch feat/large-v3-turbo 2026-04-18 16:01:40 +00:00
Sign in to join this conversation.
No reviewers
No labels
No milestone
No project
No assignees
2 participants
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
Tasch/whisper-transcribe!7
No description provided.