# SwitchLingo - container for Hugging Face Spaces (or any Docker host)
FROM python:3.12-slim
RUN apt-get update && apt-get install -y --no-install-recommends ffmpeg fonts-dejavu-core fonts-noto-core fonts-noto-cjk && rm -rf /var/lib/apt/lists/*
RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user PATH=/home/user/.local/bin:$PATH HF_HOME=/home/user/.cache/huggingface \
    OXT_DATA=/home/user/data PYTHONUNBUFFERED=1
WORKDIR /home/user/app
COPY --chown=user requirements.txt .
RUN pip install --no-cache-dir --user torch --index-url https://download.pytorch.org/whl/cpu && \
    pip install --no-cache-dir --user -r requirements.txt
# Pre-download the speech + translation models so the first visitor doesn't wait
RUN python -c "from faster_whisper import WhisperModel; WhisperModel('small', device='cpu', compute_type='int8')" && \
    python -c "from huggingface_hub import snapshot_download; snapshot_download('JustFrederik/nllb-200-distilled-600M-ct2-int8'); snapshot_download('Nextcloud-AI/madlad400-3b-mt-ct2-int8')" && \
    python -c "import transformers; transformers.AutoTokenizer.from_pretrained('google/madlad400-3b-mt')" && \
    python -c "import transformers; transformers.AutoTokenizer.from_pretrained('facebook/nllb-200-distilled-600M')" && \
    python -c "from huggingface_hub import hf_hub_download as d; [d('myshell-ai/OpenVoiceV2', f) for f in ('converter/config.json', 'converter/checkpoint.pth')]"
COPY --chown=user . .
EXPOSE 7860
CMD ["python", "-m", "uvicorn", "app.server:app", "--host", "0.0.0.0", "--port", "7860", "--proxy-headers", "--forwarded-allow-ips", "*"]