can you recommend the best traineddata for numbers and latin letters

[JenyaKirmizaTripTop]

trafficstars

I'm using tesseract for reading mrz codes and sometimes it gives me incorrect symbols eg. instead of "I" it gives me "1" or instead of "5" it gives "S"

[Shreeshrii]

Which version of tesseract and traineddata are you using?

[JenyaKirmizaTripTop]

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

[Shreeshrii]

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

[Shreeshrii]

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