faster-whisper-server / Dockerfile.cuda
Fedir Zadniprovskyi
docs: add examples, roadmap, etc.
9f56267
raw
history blame
691 Bytes
FROM nvidia/cuda:12.2.2-cudnn8-runtime-ubuntu22.04
RUN apt-get update && \
apt-get install -y curl software-properties-common && \
add-apt-repository ppa:deadsnakes/ppa && \
apt-get update && \
DEBIAN_FRONTEND=noninteractive apt-get -y install python3.11 python3.11-distutils && \
curl -sS https://bootstrap.pypa.io/get-pip.py | python3.11
RUN pip install --no-cache-dir poetry==1.8.2
WORKDIR /root/speaches
COPY pyproject.toml poetry.lock ./
RUN poetry install
COPY ./speaches ./speaches
ENTRYPOINT ["poetry", "run"]
CMD ["uvicorn", "speaches.main:app"]
ENV WHISPER_MODEL=distil-medium.en
ENV WHISPER_INFERENCE_DEVICE=cuda
ENV UVICORN_HOST=0.0.0.0
ENV UVICORN_PORT=8000