Dockerfile

FROM python:3.9-slim

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    MPLCONFIGDIR=/tmp/matplotlib \
    TRANSFORMERS_CACHE=/app/.cache/huggingface \
    HF_HOME=/app/.cache/huggingface \
    XDG_CACHE_HOME=/app/.cache \
    PYTHONIOENCODING=utf-8 \
    TOKENIZERS_PARALLELISM=false \
    HF_HUB_DISABLE_SYMLINKS_WARNING=1

WORKDIR /app

# Install system dependencies
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
    build-essential \
    curl \
    git \
    ffmpeg \
    libsndfile1 \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

# Create necessary directories with proper permissions
RUN mkdir -p /app/tmp_model /tmp/matplotlib /app/uploads /app/.cache/huggingface /app/.streamlit /app/.config /root/.cache/huggingface
RUN chmod -R 777 /app/uploads /app/tmp_model /tmp/matplotlib /app/.cache /app/.streamlit /app/.config /root/.cache
# Create symbolic link to ensure both user and root can access cache
RUN ln -sf /app/.cache/huggingface /root/.cache/huggingface

# Copy requirements first (for better caching)
COPY requirements.txt .

# Install Python dependencies with specific order for compatibility
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir torch==2.0.1 torchaudio==2.0.2 && \
    pip install --no-cache-dir -r requirements.txt && \
    pip install --no-cache-dir git+https://github.com/speechbrain/speechbrain.git@v0.5.14

# Copy source code
COPY src/ ./src/

# Copy the Streamlit directory with configuration
COPY .streamlit/ ./.streamlit/

# Set proper permissions on the Streamlit configuration
RUN chmod -R 755 ./.streamlit && \
    chmod 644 ./.streamlit/config.toml

# Expose port
EXPOSE 8501

# Health check
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health

# Run the app
ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]