audio/nes2net/Dockerfile

FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1

RUN apt-get update && apt-get install -y --no-install-recommends \
    python3 python3-pip python3-dev \
    git ffmpeg libsndfile1 wget \
    build-essential g++ \
    && rm -rf /var/lib/apt/lists/*

RUN ln -sf /usr/bin/python3 /usr/bin/python

WORKDIR /app

# Install PyTorch with CUDA 12.1
RUN pip install --no-cache-dir \
    torch==2.5.1 torchaudio==2.5.1 \
    --index-url https://download.pytorch.org/whl/cu121

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Clone fairseq with patched C extensions (same as ShiftySpeech)
RUN git clone https://github.com/facebookresearch/fairseq.git /app/fairseq_repo && \
    cd /app/fairseq_repo && \
    git checkout a54021305d6b3c4c5959ac9395135f63202db8f1 && \
    sed -i 's/ext_modules=extensions/ext_modules=[]/' setup.py && \
    pip install --no-cache-dir --no-deps -e .

COPY model_scripts /app/model_scripts
COPY api.py .
RUN mkdir -p /app/weights
COPY weights/ /app/weights/

EXPOSE 8004

RUN adduser --disabled-password --gecos '' appuser
USER appuser

CMD ["python", "api.py"]