Dockerfile

FROM nvidia/cuda:12.1.0-cudnn8-devel-ubuntu20.04
LABEL maintainer="Hugging Face"

ARG DEBIAN_FRONTEND=noninteractive

RUN apt update
RUN apt install -y git libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg
RUN python3 -m pip install --no-cache-dir --upgrade pip
# RUN apt-get install -y git libsndfile1-dev tesseract-ocr espeak-ng ffmpeg

# Prevents Python from writing pyc files.
ENV PYTHONDONTWRITEBYTECODE=1
# Open MP threads. It may need to change in production env.
ENV OMP_NUM_THREADS=1

# Keeps Python from buffering stdout and stderr to avoid situations where
# the application crashes without emitting any logs due to buffering.
ENV PYTHONUNBUFFERED=1

# ENV HF_HUB_CACHE="/hub"

WORKDIR /app

# Create a non-privileged user that the app will run under.
# See https://docs.docker.com/go/dockerfile-user-best-practices/
RUN useradd -m -u 1000 user
# Download dependencies as a separate step to take advantage of Docker's caching.
# Leverage a cache mount to /root/.cache/pip to speed up subsequent builds.
# Leverage a bind mount to requirements.txt to avoid having to copy them into
# into this layer.
RUN --mount=type=cache,target=/root/.cache/pip \
  --mount=type=bind,source=requirements.txt,target=requirements.txt \
  python3 -m pip install -r requirements.txt

# Switch to the non-privileged user to run the application.
USER user

# Copy the source code into the container.
COPY . .

# Expose the port that the application listens on.
EXPOSE 8088

# Run the application.
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]