2), 3): I'm wondering about using tesseract 4.0 for multiple language, too.
After searching & testing a while, I found that it seems not working the old method for tesseract 3. (e.g. running with '-l lang1+lang2' option) Is there any other method that I have to try? Or I have to train tesseract with two languages at the same time? 2018년 3월 10일 토요일 오후 4시 18분 48초 UTC+9, 이경준 님의 말: > > Hi i'm sorry to question oftenly. and lots of questions. > > But, I must use tesseract 4.0 for my business . > > plz understand my situations. I have lots of family to raise. > > > ealier you gave me *a bash sciprt *. In there *tesstrain.sh* (course) . > it give me an error like > > > Please make sure the TESSDATA_PREFIX environment variable is set to your > "tessdata" directory. > *Failed loading language 'chi_tra'* > Error opening data file > /usr/share/tesseract-ocr/4.00/tessdata/chi_tra.traineddata > > > *Before, you gave me a conference . it froms the lang directory / > kor.config.* > > > > > > *in there #Fixes https://github.com/tesseract-ocr/tesseract/issues/1009 > <https://github.com/tesseract-ocr/tesseract/issues/1009>preserve_interword_spaces > > 1tessedit_load_sublangs chi_tra# New Segmentation search params* > > > So I guess "tessedit_load_sublangs chi_tra" cause to error for executing > "tesstrain.sh" > > So I conclude(for solution) *1) Delete that sentence -> Is it right ? or > what is the side-effect* > > > I want to have 1 traineddata which is fine tuned and for 2 langugages > (korean & English) > > so is it possible to add the sentece like *1-1)* > > *"tessedit_load_sublangs eng"-> Is it right? or possible???* > *In conclusion * > *1)* > > > *I do not want to see like error " Please make sure the TESSDATA_PREFIX > environment variable is set to your "tessdata" directory.Failed loading > language 'chi_tra'Error opening data file > /usr/share/tesseract-ocr/4.00/tessdata/chi_tra.traineddata " * > > *2) If I want to use tessereract(4.0) for 2 languages(e.g. Korean, > English) by 1(one) traineddata(which is fine tuned) * > > Is it possible and How to make 1 finedtuned traineddata for 2 > languages(e.g Korean, English) > > 3) tesseract is possible to use like > > $ tesseract (picture.png) -l kor+eng > > is it possible ????? > > 4) What is kor.vert traineddata ? (tessdata-best) > > What is different from kor.traineddata ??? > > 5) Is it possible to fine tune by existing images??? How is it possible to > use script you gave me > -- 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 post to this group, send email to tesseract-ocr@googlegroups.com. 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/224474f7-a56f-4434-ab56-4914907fdaad%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
