diora-web/deploy/whisper/Dockerfile
mrwnslz e8bb70feb0
Some checks failed
Test / e2e (push) Waiting to run
Build and push Docker image / build (push) Successful in 19s
Test / test (push) Has been cancelled
Eingebaute Whisper-Instanz: kleiner OpenAI-kompatibler Server (lädt das Modell bei Bedarf, gibt es nach Leerlauf frei)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 11:10:15 +01:00

10 lines
517 B
Docker

# diora's built-in Whisper (docs/transcription.md). Built on the server next to diora-prod:
# docker compose build whisper
FROM python:3.12-slim
RUN apt-get update && apt-get install -y --no-install-recommends ffmpeg && rm -rf /var/lib/apt/lists/*
RUN pip install --no-cache-dir faster-whisper==1.2.1 fastapi==0.143.1 uvicorn==0.54.0 python-multipart==0.0.32
WORKDIR /app
COPY server.py .
ENV WHISPER_CACHE=/models HF_HOME=/models/hf
EXPOSE 8000
CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8000"]