I do OCR on text that is primarily in english, but has some text in hebrew characters. I scan text and save as jpeg, and then use ABBYY to convert it to Word doc.
ABBYY usually treats the punctuation in the hebrew text as if it was english. this is problematic because hebrew goes right to left, so every time there is a comma in the middle of a hebrew sentence, the word order gets garbled up.
How can I train ABBYY to read the hebrew punctuation as hebrew?