German Fraktur 18th century

Free Public AI Model for Handwritten Text Recognition with Transkribus

German Fraktur 18th century

This model has been trained on 829 400 words from the „Wien[n]erisches Diarium“ / „Wiener Zeitung“ (1703-1799), which is an Austrian newspaper. The CER on the validation set is 0.8%.
The model was created within the project „Das Wien[n]erische Diarium: Digitaler Datenschatz für die geisteswissenschafttlichen Diziplinen“ (The Wien[n]erisches Diarium: A digital data treasury for the humanities) and is provided by Claudia Resch and Dario Kampkaspar. More information can be found here: https://digitarium.acdh.oeaw.ac.at/

Contact: claudia.resch@oeaw.ac.at or dario.kampkaspar@oeaw.ac.at

Model Overview

Name:
German Fraktur 18th Century – WrDiarium_M9
Creator:
Austrian Centre for Digital Humanities and Cultural Heritage at the Austrian Academy of Sciences
Model ID:
47114
Century:
18th
Languages:
German
Script:
German Kurrent
Engine:
PyLaia
Material:
Print
CER on validation set:
0.8 %
Simply upload a picture and test this model

By uploading an image, you accept our terms and conditions and our privacy policy

German Fraktur 18th Century – WrDiarium_M9 is freely available to everyone

Get started with Transkribus and use it for your own Material
You can use this model to automatically transcribe Print documents with Handwritten Text Recgnition in Transkribus. This model can be used in the Transkribus Expert Client as well as in Transkribus Lite.
This AI model was trained to automatically convert text from images of historical German Kurrent documents into editable and searchable text.