paalberti / tesseract-dan-fraktur

Tesseract ocr training data for Danish written in fraktur script and a few other languages
Other
17 stars 9 forks source link

Various training data files for Tesseract OCR (version 3.02)

The _frak/ directories have a primitive script to compile the data files that only works on unix-like machines. If you aren't interested in working on training tesseract yourself, just find the .traineddata that is relevant for your language, save it to your tesseract installation's data directory and you should be ready for ocr.