It has been a while since I looked at Tamil. Please see https://sourceforge.net/projects/tesseracthindi/files/Tamil%20Training%20Files/
You may want to try v1 style of unicharambigs file to see if that works. Not sure if v2 is supported ... https://github.com/tesseract-ocr/tesseract/issues/165 ShreeDevi ____________________________________________________________ भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com On Wed, Sep 28, 2016 at 7:04 AM, rkvsraman <[email protected]> wrote: > > Hello, > > > I am testing the tamil data set and i am getting following issue > > பெயர் is getting recognised as டுபயர் > > and யான as யஈன > > I created the following unicharambigs file but it isnt helping. > > v2 > டுப பெ 1 > ஈ ா 1 > > I tried both 1 and 0 as type indicator but no use > > I have attached source text, image and OCred text > > I tested it with original tam.traineddata too with same result. > > > > Any suggestions? > > > -- > 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/0f16d94f-8cc7-4c50-9988-3b1eaacb333e% > 40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/0f16d94f-8cc7-4c50-9988-3b1eaacb333e%40googlegroups.com?utm_medium=email&utm_source=footer> > . > For more options, visit https://groups.google.com/d/optout. > -- 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/CAG2NduWAXNSF6Fg_TVvzS7we8jKQbqjqZ0Ar7%3D320EwkvrCdLA%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
