FROM python:3.10

WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    libffi-dev \
    libsndfile1 \
    libasound2 \
    libxt6 \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first to leverage Docker cache
COPY requirements.txt .

# Install PyTorch CPU first (2.6.0 available for CPU)
# RUN pip install --no-cache-dir torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0

RUN pip install --no-cache-dir typing-extensions==4.10.0

RUN pip install --no-cache-dir \
    torch==2.6.0+cpu \
    torchvision==0.21.0+cpu \
    torchaudio==2.6.0+cpu \
    --index-url https://download.pytorch.org/whl/cpu

# Install the rest of requirements
RUN pip install --no-cache-dir -r requirements.txt

# Download NLTK data required by g2p_en
RUN python -c "import nltk; nltk.download('averaged_perceptron_tagger_eng', quiet=True)"

# Copy application files
COPY . .

EXPOSE 7860

ENV PYTHONUNBUFFERED=1

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