b9727981cc
- Add audio setup script for PulseAudio configuration - Improve wake word detection with advanced noise filtering - Implement continuous transcription and command processing - Update speech Dockerfile with additional audio dependencies - Enhance logging and error handling in wake word detector
68 lines
1.9 KiB
Docker
68 lines
1.9 KiB
Docker
# Use Python slim image as builder
|
|
FROM python:3.10-slim as builder
|
|
|
|
# Install build dependencies
|
|
RUN apt-get update && apt-get install -y \
|
|
git \
|
|
build-essential \
|
|
portaudio19-dev \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Create and activate virtual environment
|
|
RUN python -m venv /opt/venv
|
|
ENV PATH="/opt/venv/bin:$PATH"
|
|
|
|
# Install Python dependencies with specific versions and CPU-only variants
|
|
RUN pip install --no-cache-dir "numpy>=1.24.3,<2.0.0" && \
|
|
pip install --no-cache-dir torch==2.1.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cpu && \
|
|
pip install --no-cache-dir faster-whisper==0.10.0 openwakeword==0.4.0 pyaudio==0.2.14 sounddevice==0.4.6 requests==2.31.0 && \
|
|
pip freeze > /opt/venv/requirements.txt
|
|
|
|
# Create final image
|
|
FROM python:3.10-slim
|
|
|
|
# Copy virtual environment from builder
|
|
COPY --from=builder /opt/venv /opt/venv
|
|
ENV PATH="/opt/venv/bin:$PATH"
|
|
|
|
# Install audio dependencies
|
|
RUN apt-get update && apt-get install -y \
|
|
portaudio19-dev \
|
|
python3-pyaudio \
|
|
alsa-utils \
|
|
libasound2 \
|
|
libasound2-plugins \
|
|
pulseaudio \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Create necessary directories
|
|
RUN mkdir -p /models/wake_word /audio
|
|
|
|
# Set working directory
|
|
WORKDIR /app
|
|
|
|
# Copy the wake word detection script
|
|
COPY wake_word_detector.py .
|
|
|
|
# Set environment variables
|
|
ENV WHISPER_MODEL_PATH=/models \
|
|
WAKEWORD_MODEL_PATH=/models/wake_word \
|
|
PYTHONUNBUFFERED=1 \
|
|
ASR_MODEL=base.en \
|
|
ASR_MODEL_PATH=/models
|
|
|
|
# Add resource limits to Python
|
|
ENV PYTHONMALLOC=malloc \
|
|
MALLOC_TRIM_THRESHOLD_=100000 \
|
|
PYTHONDEVMODE=1
|
|
|
|
# Add healthcheck
|
|
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
|
|
CMD ps aux | grep '[p]ython' || exit 1
|
|
|
|
# Copy audio setup script
|
|
COPY setup-audio.sh /setup-audio.sh
|
|
RUN chmod +x /setup-audio.sh
|
|
|
|
# Start command
|
|
CMD ["/bin/bash", "-c", "/setup-audio.sh && python -u wake_word_detector.py"] |