OCR different language


#1

Hi all,

I am trying to set up google OCR to work with a different language (ell),

  1. I have downloaded from tesseract the language I am interested in
  2. I insert the ell.traineddata under C:\Program Files (x86)\UiPath Studio\tessdata
  3. I changed the Language from OCR options from “eng” to “ell”

However when I execute I get the following error:

Have I missed a step? Bare in mind that when I leave it with the Language: “eng” the text is extracted (it is just jiberish)

Thank you all


How to setup the OCR language?
Read Hindi text using Ocr
How to click button in virtual machine
#2

Having this exactly same problem with finnish language pack :frowning: I’ve had this problem for months but just tried to work around it for some reason…


OCR Error
#3

And immediately after this message I downloaded the older version (v3.4) of the tessdata and it worked :expressionless: |


#4

Wow, thank you Jyrki, I tried with 3.4 and it worked !!!