Installing additional language pack for google OCR

ocr

#1

Download the trained data language file from https://github.com/tesseract-ocr/tessdata/tree/3.04.00
save file “uipath installation directory”/tessdata eg: C:\Program Files (x86)\UiPath Studio\tessdata
restart uipath studio


OCR Engines in Studio - Setup and Languages
OCR Error(traineddata v3.04)
#3

I download chinese language pack,





what’s wrong with google OCR?


Do UiPath provide the Korean language package?
#4

Try Language “chi_sim” instead of “chi-sim”.


#5

I am having the same issue

I have done the same steps as rainman, except for the hebrew language pack.
I put “heb” under language in the Google OCR function and I get the following error


#6

@tamirs, have you tried putting “heb” in the Language property for UiPath.CoreActivities.GoogleOCR? It should go where “rus” is in the screenshot below.

ocrprops

If so, and it didn’t work, make sure your heb.traineddata is in the right folder. Here’s a screenshot of where my tessdata is:

tessdata

Regards,
burque505


#7

Hey all,
so, this doesn’t seem to apply anymore, as the CE version installs on
C:\Users\<user>\AppData\Local\UiPath.
Within this folder, the only place I found
*.traineddata is
/Activities/UIPath.Vision<whatever version>/build.
Copying the .traineddata to this folder does not make the new language appear.
Any idea what to do?

Cheers
Stratum