can you recommend the best traineddata for numbers and latin letters about tessdata_best HOT 4 CLOSED

See https://github.com/tesseract-ocr/tesseract/wiki/AddOns

from tessdata_best.

Which version of tesseract and traineddata are you using?

from tessdata_best.

I'm using tess2 and i want to select which traindata will fit bettter cause i need to read from MRZ passport code, and it has such symbols '<,>', numbers and latin letters
I see some mistakes while reading <,> and also while reading latin letters. Sometimes it replaces the numbers with letters. For example 5 as S

from tessdata_best.

You may get better response to such questions on the tesseract-ocr forum.

Or open an issue on for tesseract.

You can also search for mrz.traineddata, it won't be in official repo but user contribution

from tessdata_best.