dschlueter
a986cbe42a
- stt_core.py: Whisper-Engine (einmal laden, CPU-Fallback), Audio-Dekodierung jedes Formats, Halluzinationsfilter, Äußerungserkennung per Silero-VAD - stt_service.py: /health, /v1/audio/transcriptions (OpenAI), /transcribe (Rohdaten), WS /ws/stream; Inferenz im Worker-Thread, begrenzte Warteschlange (503) - stt_wyoming.py: Home-Assistant-Anbindung (TCP 10300) - stt_cli.py: Datei/Mikrofon über den Dienst oder lokal - Tests (Unit + Integration), README, requirements.txt, deploy/stt-service.service Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
21 lines
760 B
Desktop File
21 lines
760 B
Desktop File
[Unit]
|
|
Description=SpeechToText Service (faster-whisper, HTTP :9998, Wyoming :10300)
|
|
After=network.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
WorkingDirectory=%h/Python_Programs/SpeechToText
|
|
ExecStart=%h/Python_Programs/SpeechToText/.venv/bin/uvicorn stt_service:app --host 0.0.0.0 --port 9998
|
|
Restart=on-failure
|
|
RestartSec=5
|
|
StandardOutput=journal
|
|
StandardError=journal
|
|
# GPU eindeutig per UUID (nvidia-smi -L), NICHT per Index: CUDA zählt "fastest first",
|
|
# nvidia-smi in PCI-Reihenfolge. GPU 2 = RTX 3090, teilt sich mit chatterbox-tts (~2,4 GB VRAM).
|
|
Environment="CUDA_VISIBLE_DEVICES=GPU-83ba6d1f-ebbe-f8c8-1433-153e0ebc3866"
|
|
Environment="STT_MODEL=large-v3-turbo"
|
|
Environment="STT_LANGUAGE=de"
|
|
Environment="STT_WYOMING_PORT=10300"
|
|
|
|
[Install]
|
|
WantedBy=default.target
|