missing languages from ocrfeeder that have training data
@ousia
Submitted by Pablo Rodríguez Link to original bug (#697068)
Description
Hi Joaquim,
there are some training data for languages (https://code.google.com/p/tesseract-ocr/downloads/list) that ocrfeeder doesn't list them.
Not being a comprehensive list: ancient Greek (grc) is missing from the language list and data are available.
Swedish, Danish and German have also data for Fraktur (https://en.wikipedia.org/wiki/Fraktur). These should be considered as different languages. And there are also language data for old French, Spanish and Italian.
Just in case it helps,
Pablo
Version: 0.7.x