That might work for these particular ones but what if it breaks other cases (e.g. for characters not in French)? There is no way to programmatically know what language will be the best fit for each name when names can come from every language using the Latin alphabet (in fact they don't even have to come from the Latin alphabet but that's a whole other story).
On Friday 26 July 2024 at 13:59:45 UTC+1 zdenop wrote: > tesseract img1.png - --psm 6 -l fra > Juccsus > > tesseract img2.png - --psm 6 -l fra > Bladë > > Zdenko > > > pi 19. 7. 2024 o 5:12 Péter Györök <gyorok...@gmail.com> napísal(a): > >> I'm using this command: >> tesseract file.png - --psm 6 -l script/Latin >> >> img1.png returns "JUCcCcsus" instead of "Juccsus". >> img2.png returns "Bladé" instead of "Bladë". >> >> Any suggestions on how to fix these? >> >> -- >> 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-oc...@googlegroups.com. >> To view this discussion on the web visit >> https://groups.google.com/d/msgid/tesseract-ocr/334c1f47-c957-431e-a5da-d9de11fd4531n%40googlegroups.com >> >> <https://groups.google.com/d/msgid/tesseract-ocr/334c1f47-c957-431e-a5da-d9de11fd4531n%40googlegroups.com?utm_medium=email&utm_source=footer> >> . >> > -- 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/76f4b03e-cbc5-47a5-9964-45a603a7514en%40googlegroups.com.
