Hello, I have a custom list of words that I'd like to add to (or practically substitute for) the default word list in my language. Some of these words combine letters & digits & punctuation e.g. 0.5KG 0.5L 1.1L 1.25KG 108G 4DOG
I'm using tesseract 4.0. My approach so far: - unpack lang.traineddata - create cus.lstm-word-dawg (either just from my wordlist or as combination of standard language list + my list) - create new .traineddata from cus.lstm cus.lstm-recoder cus.lstm-unicharset cus.lstm-word-dawg cus.traineddata It has practically no effect... Often, a word that actually is in the list is recognized wrongly as some string that is not in the list. I have tried to add these words using --user-words <mylist.txt>: no effect, or the same as my approach I have tried -c language_model_penalty_non_dict_word=1.0 (I thought it would limit the output to words in cus.lstm-word-dawg): no effect I'm out of ideas after two weeks of trying. Any tips, please? Thanks -- 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]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/5b015d58-9958-4c1f-a330-abdb001f7957%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
