Skip to content
Snippets Groups Projects

Whisper playground

  • Clone with SSH
  • Clone with HTTPS
  • Embed
  • Share
    The snippet can be accessed without any authentication.
    Authored by Sheogorath

    Little playground script for running whisper on any kind of audio. Mainly containerizing the step from the upstream README

    Edited
    Dockerfile 163 B
    1
    2
    3
    4
    5
    6
    7 
    FROM docker.io/library/python:3.12.3-bookworm

RUN apt-get update && apt-get install -y ffmpeg

RUN pip install -U openai-whisper==20231117

ENTRYPOINT ["whisper"]
    whisper.sh 182 B
    1
    2
    3
    4
    5 
    #!/bin/bash

podman build -t whisper .

exec podman run --rm -it -v "$HOME/.cache/whisper:$HOME/.cache/whisper:z" -v "$(pwd):$(pwd):z" -w "$(pwd)" whisper audio.mp3 --model medium.en
    0% or .
    You are about to add 0 people to the discussion. Proceed with caution.
    Finish editing this message first!
    Please register or to comment