Hi Florian. The only training included with Tesseract that uses bigram dawg files is eng, and the eng.config only has these 2 relevant entries:
load_bigram_dawg True tessedit_enable_bigram_correction True So I guess you're providing Tesseract all it needs. You could look for the "verified by bigram model" reference in the code and see if there is any useful nearby code that is controlled by a config variable. I don't think many people use bigram dawgs, so it's possible it isn't very mature / useful. The cube code seems to be lots more bigram focused, but we can't train for that yet... Good luck, and let us know how you get on. Nick -- -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en --- 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 [email protected]. For more options, visit https://groups.google.com/groups/opt_out.
