The dataset contains more than #7 thousands images (.tif) with ground truth (.gt.txt) from Google image augmented with few synthetic data.
The dataset is ready to be used to train with Tesseract v4.
If you're lazy and don't want to train the model by yourself then, try the ones under tessdata_best (float-model) or tessdata_fast (int-model) folders.
You can check how accurate the model is at https://www.doubango.org/webapps/mrz/
To get help: https://groups.google.com/forum/#!forum/doubango-ai