anotherjesse / whisper-updated

test of replicate.com/openai/whisper updated with more recent ubuntu/cudann

  • Public
  • 291 runs
  • GitHub
  • Paper
  • License
Run with an API
Playground API Examples README Versions

Run time and cost

This model costs approximately $0.023 to run on Replicate, or 43 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 104 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This is a TEST of building https://replicate.com/openai/whisper with a newer version of ubuntu & ffmpeg & cudnn…

See https://replicate.com/openai/whisper to learn more about this model.

See https://github.com/chenxwh/cog-whisper/issues/2 for details of why I built this.

There are NO changes to the code in chenxwh’s port to replicate. The change is to the tool cog which generates the model that is run on replicate. This should support newer m4a and mp4 files generated by Apple products

This model will be deleted after determining how to send a PR to https://github.com/chenxwh/cog-whisper to support more recent FFMPEG