Persian support in Tesseract

[ghost]

Would you be willing to add support for Persian language?

There is an on-going project here https://github.com/reza1615/PersianOcr I tested with "per.traineddata" and it works well on my end.

Thank you

[zdenop]

tessdata files are generated by google and they provide support for including langdata.
IMO community trainings (e.g. not supported by google) should be separated from google data.

[jimregan]

Persian data may be coming in the future (it was added to langdata).

[ghost]

good news thank you @zdenop and @jimregan

[theraysmith]

Persian traineddata and training data is included in tessdata and langdata respectively.
The language code is fas (ISO 639-2T), NOT per, which uses the disfavored ISO 639-2B. (See https://en.wikipedia.org/wiki/Talk%3AISO_639-2).

Having said all that, the accuracy is probably appalling, but I would be happy to know if it works at all.

[ghost]

Awesome!

[mafshin]

Thank you @theraysmith , the key missing explanation .. fas not per :-)

[Shreeshrii]

@PepLamb @mafshin @reza1615

Please test with the latest BEST 4.0alpha traineddata and provide feedback at #70