Where to put model in local install

[remybonnav]

I don't get how I can link to the model on a local indtall. Should I replace /openai/largev2/ by the path of my model on the disk?
And should I download all feom the folder from huggingface or should I just download the flax file?

[sanchit-gandhi]

Hey @remybonnav!

Cool to see that you're using the Whisper JAX repo 🤗 You have two options for using your own checkpoint:

1. Replace openai/large-v2 with the id of your checkpoint on the Hugging Face Hub, e.g. for this checkpoint, I would use sanchit-gandhi/whisper-small-hi
2. Download the entire repository to your local system, and then pass the path to this folder. E.g. if I cloned this checkpoint into a folder called whisper-small-hi, I would pass ./whisper-small-hi

[remybonnav]

Great, thanks, I was not sure how to replace path to huggingface by a path to local folder. Thanks again