When you are using pytesseract to recognize chinese from an image, you may get an error: Failed loading language ‘chi_sim’. In this tutorial, we will introduce you how to fix.
Download chi_sim.traineddata
You can download this file in here:
https://github.com/tesseract-ocr/tessdata
Copy chi_sim.traineddata to tessdata directory
You should copy this file to tessdata directory.
Then run you python code, you will find this error is fixed.
If you find error: TesseractError eng.traineddata Please make sure the TESSDATA_PREFIX environment variable
You can refer:
Fix TesseractError eng.traineddata Please make sure the TESSDATA_PREFIX environment variable