Dockerfile

FROM nvidia/cuda:11.8.0-devel-ubuntu22.04

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV LANG=C.UTF-8

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    python3.10 \
    python3.10-dev \
    python3-pip \
    git \
    build-essential \
    cmake \
    gcc \
    g++ \
    libsndfile1 \
    sox \
    libsox-dev \
    libsox-fmt-all \
    && rm -rf /var/lib/apt/lists/*

# Upgrade pip
RUN python3.10 -m pip install --upgrade pip setuptools wheel

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

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Clone and install NeMo
RUN git clone https://github.com/AI4Bharat/NeMo.git && \
    cd NeMo && \
    git checkout nemo-v2 && \
    pip install -e . && \
    python3.10 -c "import nltk; nltk.download('punkt')"

# Copy application code
COPY app.py ./app.py

# Create directory for temporary files
RUN mkdir -p /tmp/audio_files

# Expose port
EXPOSE 8000

# Command to run the application
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]