metadata

license: mit
language:
  - de
metrics:
  - cer
library_name: transformers
tags:
  - kurrent
  - ocr
  - htr
  - 19th century

TrOCR Kurrent-Model 19th century

Base model: microsoft/trocr-base-handwritten

Train Lines: 292'997
Eval Lines: 7'513
Test Lines: 15'817

Epochs: 19.66 / 20
Eval CER: 0.02827
Test CER: 0.02655

Finetuned on Kurrent-dataset, containing:

Material from the State Archives of Zurich ("Regierungsratsprotokolle"), provided by the State Archives of Zurich
Lecture notes of Humboldt Lectures, provided by the Berlin-Brandenburgian Academy of Sciences
Diary of Eugen Huber, provided by the University of Zurich
Handwritting and Copies by and of Gottfried Semper
Konzilsprotokolle, University of Greifswald (19th century)
as well as many other smaller collections/examples