Are lang.unicharambigs and lang.singles_text language dependent or script dependent? Let's assume I want to train for Fraktur script for German language and I have langdata for regular German already - can I use deu.unicharambigs and deu.singles_text from there or should I generate them somehow depending on my Fraktur font?
Thank you! On Mon, Aug 16, 2021 at 6:49 PM Sim Tov <smn...@gmail.com> wrote: > Hello, > > I'm learning how to train tesseract for a new script and one of the stages > is generating langdata. > > I saw the examples here: > > https://raw.githubusercontent.com/tesseract-ocr/langdata_lstm > > I can provide lang/lang.training_text and lang/lang.wordlist > > What is the purpose of the rest of the files? E.g. lang.unicharambigs and > lang.singles_text? Do they depend on lang/lang.training_text and > lang/lang.wordlist and if yes - how do I generate them? > > Thank you! > -- 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/CA%2BX_a%2Byiuf%3DikfrHLg%2Bb2NO5N05%3Dz7pJW98%3DJUkw%2BmdFcDhnOA%40mail.gmail.com.
