Real-time speech-to-text using OpenAI Whisper (faster-whisper). Features browser audio capture, WebSocket streaming, and customizable display settings. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
55 lines
1.5 KiB
Docker
55 lines
1.5 KiB
Docker
# GPU-enabled Dockerfile for NVIDIA CUDA support
|
|
FROM nvidia/cuda:12.1.0-cudnn8-runtime-ubuntu22.04
|
|
|
|
# Set environment variables
|
|
ENV PYTHONDONTWRITEBYTECODE=1
|
|
ENV PYTHONUNBUFFERED=1
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
|
|
# Install Python and system dependencies
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
python3.11 \
|
|
python3.11-venv \
|
|
python3-pip \
|
|
ffmpeg \
|
|
libsndfile1 \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Set Python 3.11 as default
|
|
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.11 1 \
|
|
&& update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1
|
|
|
|
# Create app directory
|
|
WORKDIR /app
|
|
|
|
# Create non-root user
|
|
RUN useradd -m -u 1000 appuser
|
|
|
|
# Copy requirements first for better caching
|
|
COPY requirements.txt .
|
|
|
|
# Install Python dependencies
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
|
|
|
# Copy application code
|
|
COPY . .
|
|
|
|
# Create data and recordings directories
|
|
RUN mkdir -p /app/data /app/recordings && chown -R appuser:appuser /app
|
|
|
|
# Create directory for Whisper models cache
|
|
RUN mkdir -p /home/appuser/.cache/huggingface && chown -R appuser:appuser /home/appuser
|
|
|
|
# Switch to non-root user
|
|
USER appuser
|
|
|
|
# Expose port
|
|
EXPOSE 5000
|
|
|
|
# Health check
|
|
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
|
|
CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:5000/api/health')" || exit 1
|
|
|
|
# Run the application
|
|
CMD ["python", "app.py"]
|