Edit model card

mT5 OCR cleaning model

For further models, scripts and details, see or our demo site.

  • Pretrained model used: mT5-base
  • Prefix: "trans: "

Limitations

  • max_source_length = 256
  • max_target_length = 256

Citation

If you use this model, please cite the following paper:


@inproceedings {laki-ocr,
    title = {OCR hibák javítása neurális technológiák segítségével},
    booktitle = {XVIII. Magyar Számítógépes Nyelvészeti Konferencia},
    year = {2022},
    publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
    address = {Szeged, Magyarország},
    author = {Laki, László and and Kőrös, Ádám and Ligeti-Nagy, Noémi and and Nyéki, Bence and Vadász, Noémi and Yang, Zijian Győző and Váradi Tamás},
    pages = {417--430}
}
Downloads last month
10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.