Federated finetuning of Whisper on Raspberry Pi 5

I don't think the article mentions it, how well does the rpi 4 and 5 do for inference with whisper especially v3?

How would this actually work in practice? Do I ask the user to utter specific words then train on that? How is it different from the traditional speech recognition that I need to &#x27;train&#x27; to work better on my voice?<p>The Holy Grail would be to train the model while using it, without any friction. I don&#x27;t think these methods support that though.

This is cool. This might be a silly question, but what are the scenarios where it&#x27;s useful for fine-tuning on the edge with small devices? I get inference on the edge, and curious about metrics on that for Whisper, but isn&#x27;t it better to fine-tune on beefier infrastructure and then deploy it for inference on the edge?

I’m guessing this will also help with thick accents?