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