Using Custom Language Files

Iron Tesseract OCR fully supports custom or downloaded languages and fonts following the Tesseract .traineddata file format standard (version 4 or above). You can find such files commonly on [Github.com]().

If you wish to train your own custom font support or language pack, we recommend reading our tutorial on creating custom tesseract language packs.

How to Use Tesseract Languages For OCR

  1. Install an OCR library to choose Tesseract Language options.
  2. Construct a IronTesseract object.
  3. Provide the custom language file while using UseCustomTesseractLanguageFile.
  4. Create a OcrInput object using the image path as a parameter.
  5. Pass the OcrInput object to the Read method to read the text in language.