CPU version

[AGRocky]

Hey team, first of wonderful I have a few questions:

1. How is it different from any other OCR model for is it confined only for extraction or anything else.
2. Is there a model available which can run on CPU or on local machine.

Please do let me know on the above two queries it would be deeply appreciated.

Thanks in advance.

[shikharpant]

I tried doing it in a MacBook m1 but alas for the cuda support or rather lack thereof. Changing cuda to mps in run_ocr_2.0.py did not help at all. got stuck with

TypeError: Trying to convert BFloat16 to the MPS backend but it does not have support for that dtype.

[ElvisClaros]

Hello, it worked for me, I made a pull request