theresfj · PyLaia · Published November 11, 2024

19th century Schochisk Fractur

Text Recognition

Description

The model is based on the printed version of "Norges Gamle Love" ("Old Norwegian Law") vol. 1&2 from 1846 and 1848. The type used in the print is both schochisk fractur (main text) and Antiqua (preface and footnotes), and the model should be able to read both. Schochisk fractur is named after the designer, Friedrich Schoch, Ausburg, Germany. The model was made by Therese Foldvik (University of Oslo), and the work coordinated by prof. Anders Winroth (University of Oslo).

Try this model

19th century Schochisk Fractur
Use this modelOpen in Transkribus
Very low error rate0.02% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 0.02% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material.

Measured on the model's own validation data. Results on your documents may differ depending on handwriting style, document condition, language, and how closely your material resembles the training data.

Words64,063
Lines5,182
Training Pages142
Model ID216333
Languages
DanishNorseNorwegian
Centuries
19th c.