Strangely, the ara language model only seems to have the first two numerals, but the Arabic script model has them all:
$ grep [٠١٢٣٤٥٦٧٨٩] ara.lstm-unicharset ٠ 8 0,255,0,255,0,0,0,0,0,0 Arabic 82 5 82 ٠ # ٠ [660 ]0 ١ 8 0,255,0,255,0,0,0,0,0,0 Arabic 83 5 83 ١ # ١ [661 ]0 $ grep [٠١٢٣٤٥٦٧٨٩] script/Arabic.lstm-unicharset ٠ 8 0,255,0,255,0,0,0,0,0,0 Arabic 82 5 82 ٠ # ٠ [660 ]0 ١ 8 0,255,0,255,0,0,0,0,0,0 Arabic 83 5 83 ١ # ١ [661 ]0 ٩ 8 0,255,0,255,0,0,0,0,0,0 Arabic 102 5 102 ٩ # ٩ [669 ]0 ٨ 8 0,255,0,255,0,0,0,0,0,0 Arabic 217 5 217 ٨ # ٨ [668 ]0 ٣ 8 0,255,0,255,0,0,0,0,0,0 Arabic 218 5 218 ٣ # ٣ [663 ]0 ٢ 8 0,255,0,255,0,0,0,0,0,0 Arabic 219 5 219 ٢ # ٢ [662 ]0 ٧ 8 0,255,0,255,0,0,0,0,0,0 Arabic 222 5 222 ٧ # ٧ [667 ]0 ٥ 8 0,255,0,255,0,0,0,0,0,0 Arabic 223 5 223 ٥ # ٥ [665 ]0 ٤ 8 0,255,0,255,0,0,0,0,0,0 Arabic 224 5 224 ٤ # ٤ [664 ]0 ٦ 8 0,255,0,255,0,0,0,0,0,0 Arabic 300 5 300 ٦ # ٦ [666 ]0 With -l Arabic using the tessdata_best model, I get: السيدة : نهى الامام الشيخ رقم العضوية : ۸ ٥۸٥ 6 رقم الايصال : ۱۰۹۲١٤ تاريخ السداد : ۲٠۲۰/۰۱/۰٢ www.alshams.club ا ۱ ئيس مجلس الادارة @alshams.club goo info “f m الاعلامي د/ انامه ابو On Thursday, November 2, 2023 at 12:03:53 PM UTC-4 mosta....@gmail.com wrote: I tried to get the data of this picture the this is the output ! : 7 عضو عامل السيدة : نهى الامام الشيخ رقم العضوية : ??????? . رقم الايصال : ?????????? تاريخ السداد : ?????/??/??? ا » | >ا.ن.»»» رتيس معا ادارة “ ا. 7 الاعلامي د/ اسفة On Thursday, 2 November 2023 at 18:01:28 UTC+2 Mostafa Abdo wrote: I need to get Eastern Arabic numbers. I tried ara.traineddata , Arabic.traineddata and ara-Amiri.traineddata of Tessdata folder all don't have the Arabic (Eastern) numbers I am using Java with tess4j-5.8.0 library -- 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/e1ba26bc-8806-40f7-a111-80d67bfc673dn%40googlegroups.com.
