hovevideo / stable-whisper

Transcribe audios using OpenAI's Whisper with stabilizing timestamps by stable-ts python package.

  • Public
  • 133 runs
  • T4
  • GitHub
Iterate in playground
  • Prediction

    hovevideo/stable-whisper:a6fcb78a1972604577d832d3e3c3989cd87cb76a1c8d3fa08d6b939e44392c50
    ID
    zh2caw362srge0cfbswava6c5w
    Status
    Succeeded
    Source
    Web
    Hardware
    T4
    Total duration
    Created

    Input

    url
    https://replicate.delivery/pbxt/Js2Fgx9MSOCzdTnzHQLJXj7abLp3JLIG3iqdsYXV24tHIdk8/OSR_uk_000_0050_8k.wav

    Output

    Generated in

Want to make some of these yourself?

Run this model