Hi, i successfully trained my first model (german language); now i want to improve accuracy by using specialized dictionaries. When using a bigram-dawg, i see no effect at all; i turned on debugging (by using "tessedit_bigram_debug 3" in config), all i see is confirmations of top choices (e.g. "Top choice 'oder anderer' verified by bigram model.") but no correction of "near" hits. Also even more strangely, some times i see verifications of bigrams that are not in my provided dawg!
Do I need another magic switch to activate bigram correction? For now i have "load_bigram_dawg T" and "tessedit_enable_bigram_correction T" in my config-file provided in the .traineddata. Thanks for help! Florian -- -- 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.
