FAQ

How Do I Add Languages to the Generate OCR Files Workflow?

The Generate OCR Files workflow uses Google Tesseract to perform OCR. In order, for Tesseract to do that, it needs the Tesseract language data files. These files can be found on the internet here for individual languages or here for the full language set.

These language data files must be extracted to your Tessdata Directory.

Generate OCR Files Workflow Has No Languages

Speedwagon cannot find the required language data files on your computer. See How Do I Add Languages to the Generate OCR Files Workflow?

What Tools Are You Using in Speedwagon?

  • Python 3

  • PyQt for generated the GUI

  • CMake to generate standalone installable packages

  • Google Tesseract for producing OCR

  • Exiv2 for inspecting embedded image metadata

  • Kakadu for creating JPEG2000 images