# Forced-aligner sidecar: word-level timing with torchaudio MMS_FA. Not part of the app image.
#   CPU (default):  docker compose up -d --build tts-aligner
#   GPU (optional): docker compose --profile gpu up -d --build tts-aligner-gpu
FROM python:3.12-slim-bookworm
ARG TORCH_INDEX=https://download.pytorch.org/whl/cpu
ENV PYTHONUNBUFFERED=1 PIP_NO_CACHE_DIR=1 TORCH_HOME=/models/torch HF_HOME=/models/hf
RUN apt-get update && apt-get install -y --no-install-recommends libsndfile1 curl \
    && rm -rf /var/lib/apt/lists/*
COPY requirements.txt /tmp/requirements.txt
RUN pip install --index-url "$TORCH_INDEX" torch==2.10.0 torchaudio==2.10.0 \
    && pip install -r /tmp/requirements.txt
RUN useradd --uid 10001 --no-create-home --shell /usr/sbin/nologin aligner && mkdir -p /models && chown aligner /models
WORKDIR /srv
COPY app.py .
USER aligner
EXPOSE 8000
HEALTHCHECK --interval=30s --timeout=5s --start-period=60s --retries=3 \
    CMD curl -fsS http://127.0.0.1:8000/health || exit 1
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "1", "--no-access-log"]