Hi Donaldo, I don't see any Esperanto language file in the main site. Perhaps someone contributed the training to a Linux distro -- I see it in Ubuntu. You can get the "epo.traineddata" file and improve the training following the FAQ on the Tesseract OCR website. When you've made an improved version you could contribute it to the project. Someone named Judith asked about Esperanto on the list before -- she wanted to help but she didn't have technical knowhow. --Sven
On Wed, Sep 5, 2012 at 6:09 PM, Donaldo <[email protected]> wrote: > I am running tess version 3.02 on Linux Mint 13 KDE. I have installed the > tesseract-ocr and tesseract-ocr.epo packages. > I used the command: tesseract monato.tiff test-monato -l epo > > The accuracy for accented Esperanto letters (ĉĝĥĵŝŭ) was zero, while for > non-accented letters it was about 99%. > > I also tried the free web service at http://www.newocr.com and got similar > results. It says it uses Tesseract for Esperanto. > > Where are the training files that someone has used for Esperanto training? > What needs doing? > > Regards, > Donaldo > > > -- > 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 -- ``All that is gold does not glitter, not all those who wander are lost; the old that is strong does not wither, deep roots are not reached by the frost. >From the ashes a fire shall be woken, a light from the shadows shall spring; renewed shall be blade that was broken, the crownless again shall be king.” -- 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
