While trying to test the legacy traineddata for Arabic, I tested all recent versions from 4.1 and above, none of them seems to support legacy trained data of Arabic language (ara). After more research I've found out that the latest commit says in tessdata:
- ara.traineddata <https://github.com/tesseract-ocr/tessdata/blob/main/ara.traineddata> - removed legacy model from indic and arabic script languages <https://github.com/tesseract-ocr/tessdata/commit/cdd8a9ec438fc0b9f21635466196fe1c05efca16> Now I'm trying to install tesseract 4.00 on my Ubuntu 20.04 machine. Is there a binary build or an installation guide for tesseract-ocr 4.00 Focal ? -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/17e8a099-efb1-463d-86b2-17240aab5c49n%40googlegroups.com.