fix(stt): CUDA-OOM vermeiden + Fehlermeldung bei leerer Transkription verbessern
- .env: FASTER_WHISPER_DEVICE=cpu gesetzt; llama.cpp belegt GPU 1 komplett, faster-whisper (small-Modell) laeuft problemlos auf CPU (~1-2s Latenz) - ws.py: "empty transcript" -> "Keine Sprache erkannt — bitte erneut sprechen." Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
parent
6693c0411c
commit
6d63b8d063
1 changed files with 4 additions and 1 deletions
|
|
@ -209,7 +209,10 @@ async def _voice_turn(websocket, store, user, session_id, audio, fmt, options):
|
|||
return
|
||||
await websocket.send_json({"type": "transcript", "text": transcript})
|
||||
if not transcript or not transcript.strip():
|
||||
await websocket.send_json({"type": "error", "detail": "empty transcript"})
|
||||
await websocket.send_json({
|
||||
"type": "error",
|
||||
"detail": "Keine Sprache erkannt — bitte erneut sprechen.",
|
||||
})
|
||||
return
|
||||
await _run_turn(websocket, store, user, session_id, route, orchestrator, output, transcript, options)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue