Provide more information on LANG_TYPE in the documentation

[giri-kum]

Is there a lookup table of LANG_TYPE for all the languages that tesseract support?

[stweil]

Please give more details. What do you mean by "lookup table of LANG_TYPE"?

[giri-kum]

@stweil By that I meant, what LANG_TYPE is used for each languages during training. The documentation here says that https://github.com/tesseract-ocr/tesstrain defines the LANG_TYPE which can take Indic, RTL or blank.

I assume it is blank for English, Indic for Hindi, RTL for Arabic. It would be helpful while finetuning if we have this list as a lookup table for all the traineddata files that are present in the tessdata repository.