From Old Icelandic HTR Outputs to Normalised Texts through Seq2Seq Transformers

Sep 8, 2026, 9:30 AM
30m
Room 3

Room 3

Speaker

Nikola Krisztian Czindrity (University of Vienna)

Description

For an Old Icelandic manuscript-to-edition pipeline, we train a 10M-parameter PyTorch CharSeq2Seq Transformer to transform facsimile-like transcriptions into diplomatic transcriptions (facs2dipl task) and, in turn, into normalised ones (dipl2norm task; https://huggingface.co/NKCZ/old-icelandic-facs2dipl2norm).

We train the model on around 30,000 line-level triples of facsimile-like, diplomatic, and normalised transcriptions from three MENOTA editions of manuscripts edited by Andrea de Leeuw van Weenen. The facsimile-like transcriptions from these editions also constitute a substantial part of the training data for the OICEN-HTR model.

We evaluate CER on in-domain test set and on 200 lines from two out-of-domain manuscripts, comparing our model with frequency-based lookup tables and GPT-5.6 Luna in zero- and few-shot settings. We separately fine-tune the model on 500 lines from each out-of-domain manuscript. The base model outperforms the alternative methods on in-domain test set(CER 0.01 and 0.03), while the fine-tuned models perform best on their respective out-of-domain manuscripts (CER 0.05 and 0.12; 0.08 and 0.07). Finally, applied to HTR output from the Kringla fragment (HTR CER 0.16), the model achieves CERs of 0.20 and 0.22 for the two transformation tasks."

Presentation materials

There are no materials yet.