This is an implementation of Whisper as a Cog model using the latest available version and adding more inputs in the predict function. Cog packages machine learning models as standard containers.
First, run get_weights.sh
from the project root to download pre-trained weights:
./scripts/get_weights.sh
You can then build a container and run predictions like so:
cog predict -i audio="<path/to/your/audio/file>"
To publish the model to Replicate, run:
cog login
cog push r8.im/<your-username>/<your-model-name>