Low-energy dockerfile for WhisperX
WhisperX is unmaintained, use a fork that at least pays attention to dependencies.
Update of this
FROM pytorch/pytorch
RUN apt update
RUN apt install -y git
RUN pip install git+https://github.com/federicotorrielli/BetterWhisperX
RUN python -c 'from faster_whisper.utils import download_model; download_model("large-v3")'
Run with:
docker run -it --entrypoint /bin/bash -v'/home/joregan/tmpf:/audio' --gpus all whisperx