How to train data for read OCR?

I want to read file PDF by use OCR but It many format , So I want to train data for read OCR.

Please guide me about it.

I recommend using the Digitize Document activity.

It will give you the PDF text, it’ll work with native PDFs and scanned ones and you can use the results for document understanding as well.

You can use different OCR engines like the ones from UiPath, OmniPage or others.
Here’s an overview of the different OCR engines:

But I’m pretty sure you cannot train the OCR engines themselves, at least not with UiPath.

You can however train a document understanding model.
More on document understanding can be read here: Introduction

If this has helped you, please mark this answer as the solution.

1 Like