Dockerfile

# Dockerfile for Nemotron Speech Streaming
# FastAPI + WebSocket + NeMo ASR

FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    DEBIAN_FRONTEND=noninteractive

# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.10 \
    python3-pip \
    python3.10-dev \
    ffmpeg \
    libsndfile1 \
    git \
    && rm -rf /var/lib/apt/lists/*

# Set Python 3.10 as default
RUN ln -sf /usr/bin/python3.10 /usr/bin/python3 && \
    ln -sf /usr/bin/python3.10 /usr/bin/python

WORKDIR /app

# Install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY main.py .
COPY static/ ./static/

# Create non-root user for security
RUN useradd --create-home --shell /bin/bash appuser && \
    chown -R appuser:appuser /app
USER appuser

# Expose port
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:7860/health')" || exit 1

# Run the application
CMD ["python", "-m", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]