PdfCraft's text recognition (Scan & OCR) uses these models, unmodified.

text-detection.rten
  Ocrs text detection model
  by Robert Knight (ocrs-models; trained on HierText, CC-BY-SA-4.0)
  from https://github.com/robertknight/ocrs-models (the models ocrs downloads; model card: https://huggingface.co/robertknight/ocrs, cc-by-sa-4.0)
  licence: CC-BY-SA-4.0 (https://creativecommons.org/licenses/by-sa/4.0/legalcode.txt; full text in text-detection.rten.LICENCE.txt)

text-recognition.rten
  Ocrs text recognition model
  by Robert Knight (ocrs-models; trained on HierText, CC-BY-SA-4.0)
  from https://github.com/robertknight/ocrs-models (the models ocrs downloads; model card: https://huggingface.co/robertknight/ocrs, cc-by-sa-4.0)
  licence: CC-BY-SA-4.0 (https://creativecommons.org/licenses/by-sa/4.0/legalcode.txt; full text in text-recognition.rten.LICENCE.txt)

text-recognition-cyrillic.rten
  PaddleOCR cyrillic_PP-OCRv5_mobile_rec recognition model, converted for rten
  by PaddlePaddle
  from https://huggingface.co/PaddlePaddle/cyrillic_PP-OCRv5_mobile_rec_onnx (ONNX; converted with rten-convert 0.22.0 to opset 10)
  licence: Apache-2.0 (https://www.apache.org/licenses/LICENSE-2.0.txt; full text in text-recognition-cyrillic.rten.LICENCE.txt)
