Donut Base Encoder

🚀 Donut (base-sized model, pre-trained only)

A pre-trained Donut model introduced in the paper OCR-free Document Understanding Transformer, designed for document-related tasks.

Disclaimer: The team releasing Donut did not write a model card for this model so this model card has been written by the Hugging Face team.

📚 Documentation

Model description

Donut Encoder consists of a vision encoder (Swin Transformer). Given an image, the encoder encodes the image into a tensor of embeddings (of shape batch_size, seq_len, hidden_size).

Intended uses & limitations

This model is meant to be fine-tuned on a downstream task, like document image classification or document parsing. See the model hub to look for fine-tuned versions on a task that interests you.

How to use

We refer to the documentation which includes code examples.

BibTeX entry and citation info

@article{DBLP:journals/corr/abs-2111-15664,
  author    = {Geewook Kim and
               Teakgyu Hong and
               Moonbin Yim and
               Jinyoung Park and
               Jinyeong Yim and
               Wonseok Hwang and
               Sangdoo Yun and
               Dongyoon Han and
               Seunghyun Park},
  title     = {Donut: Document Understanding Transformer without {OCR}},
  journal   = {CoRR},
  volume    = {abs/2111.15664},
  year      = {2021},
  url       = {https://arxiv.org/abs/2111.15664},
  eprinttype = {arXiv},
  eprint    = {2111.15664},
  timestamp = {Thu, 02 Dec 2021 10:50:44 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2111-15664.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

📄 License

This model is released under the MIT license.