Surya () already supports line detection , and I'm excited to have it do full end to end OCR.
The final model should support ~90 languages (all major languages in use today).
An update on surya text recognition - I'm happy with the data/architecture, and I'm ready to scale up training.
Here are some results from a (very) early checkpoint. Left is original, right is OCR (Malayalam)
I want to get the training done in the next week or two.
My
@LambdaAPI
4x A6000s have been great, but I think I'm going to need more to scale up this training. If you know of any discounted/available GPUs (ideally 8x 80GB {A,H}100), please let me know.