Oliver/video-accessibility
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat: upgrade Whisper model from base to large-v3

Browse source 
Uses the multilingual large model for more accurate transcription
and sentence boundary detection.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
michael 2025-12-28 21:20:03 -06:00
parent 582f9f066e
commit 614ff841fe
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
backend/app/core/config.py
View file

@ -165,7 +165,7 @@ class Settings(BaseSettings):
gemini_tts_speed_step: float = 0.1
# Whisper Configuration (for pause point refinement)
whisper_model: str = "base" # Options: tiny, base, small, medium, large-v3
whisper_model: str = "large-v3" # Options: tiny, base, small, medium, large-v3
whisper_max_search_window: float = 5.0 # Max seconds to search for speech gap after Gemini point
whisper_sentence_gap_threshold: float = 0.5 # Gap duration to classify as sentence boundary
whisper_phrase_gap_threshold: float = 0.3 # Gap duration to classify as phrase boundary