On Wed, Aug 22, 2012 at 05:50:06PM +0300, Jani Monoses wrote: > So there's no way of just adding new words to the existing dictionary > without redoing the whole training?
There is a way, yes. Create a ron.user-words file in your tessdata directory, and a config file stating: user_words_suffix user-words (I think the config file is needed, but I'm not sure.) The ron.user-words file should have a list of words, one per line, UTF8 encoded. > Are any other tunables such as the above that you think may help looking into? I found 'enable_new_segsearch 1' to be very helpful, but it might already be enabled with Romanian (use combine_tessdata -u and check the .config file if you want to see). Other than that, I can't advise really. There isn't any documentation for most of the configuration variables, so they're in the realm of "black magic". grep -R VAR_H * | grep -v '^Binary '| grep -v 'svn-base' on the source tree will give you a listing of things to try if you feel like exploring. 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
