Hi
is there a way to ocr a document containing two languages, as per my search, tesseract can have two languages as arguments, but i couldn’t find a way to pass that in Mayan.
We have so many documents in arabic language, but dates, emails, document IDs, numbers and amounts ,and so many critical information are in english. the ocr output of these documents renders those information unusable with multiple errors eventhough the overall ocr text is near perfect.
thanks