Skip to content

C
coderai
Switch branch/tag
Find file
BlameHistoryPermalink
  • Your Name's avatar
    Complete fix: Add ondemand mode model switching to audio and TTS endpoints · 63460a13
    Your Name authored 
    - Added model resolution and unload logic to /v1/audio/transcriptions
- Added model resolution and unload logic to /v1/audio/speech (TTS)
- Now ALL endpoints (text, image, audio, TTS) properly handle model switching
- In ondemand mode, ANY model type switch triggers unload first (e.g., text->audio, TTS->image, etc.)
    63460a13
transcriptions.py 7.92 KB