Dockerfile

FROM python:3.10-slim

WORKDIR /app

# espeak-ng is required by phonemizer for English text-to-phoneme conversion
RUN apt-get update && apt-get install -y ffmpeg espeak-ng \
    && rm -rf /var/lib/apt/lists/*

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

# Pre-download both English models at build time
RUN python -c "from transformers import VitsModel, AutoTokenizer; VitsModel.from_pretrained('facebook/mms-tts-eng'); AutoTokenizer.from_pretrained('facebook/mms-tts-eng')"
RUN python -c "from transformers import VitsModel, AutoTokenizer; VitsModel.from_pretrained('kakao-enterprise/vits-vctk'); AutoTokenizer.from_pretrained('kakao-enterprise/vits-vctk')"

COPY app.py .

EXPOSE 7860
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]