Papers › Transformer-based HTR for Historical Documents

Transformer-based HTR for Historical Documents

21 Mar 2022arXiv:2203.11008archive 2025-07-28

Phillip Benjamin Ströbel, Simon Clematide, Martin Volk, Tobias Hodel

We apply the TrOCR framework to real-world, historical manuscripts and show that TrOCR per se is a strong model, ideal for transfer learning. TrOCR has been trained on English only, but it can adapt to other languages that use the Latin alphabet fairly easily and with little training material. We compare TrOCR against a SOTA HTR framework (Transkribus) and show that it can beat such systems. This finding is essential since Transkribus performs best when it has access to baseline information, which is not needed at all to fine-tune TrOCR.

PaperPDFCode

Code

EriCongMa/awesome-transformer-ocr mentioned on GitHubpaddle report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

HTRTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTrOCR

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections