Dockerfile

FROM python:3.11-slim

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1

# ffmpeg is required to extract audio from uploaded videos
RUN apt-get update \
 && apt-get install -y --no-install-recommends ffmpeg git \
 && rm -rf /var/lib/apt/lists/*

# Run as a non-root user (recommended for Spaces)
RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH \
    HF_HOME=/home/user/.cache/huggingface

WORKDIR $HOME/app

# Install dependencies first for better layer caching
COPY --chown=user requirements.txt .
RUN pip install --no-cache-dir --upgrade pip \
 && pip install --no-cache-dir -r requirements.txt

# Pre-download the Whisper model at build time so the first run is fast
RUN python -c "from transformers import pipeline; pipeline('automatic-speech-recognition', model='openai/whisper-base')"

COPY --chown=user . .

EXPOSE 7860

CMD ["python", "app.py"]