National Archives of Norway · PyLaia · Published December 12, 2022

Haugianerbrev Transcripts

Text Recognition

Description

The model is based on Danish-Norwegian transcripts from the 20th century of “Samlinger til kildeutgivelse, Haugianerbrev” (1760–1842) at the National Archives of Norway. The documents have running text with the occasional handwritten notes and corrections.

Try this model

Use this modelOpen in Transkribus
Very low error rate0.5% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 0.5% 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.

Words23,994
Lines2,233
Training Pages55
Model ID48699
Languages
DanishNorwegian
Centuries
20th c.