National Archives Netherlands · PyLaia · Published December 23, 2022

Typewritten/print_early_1900

Text Recognition

Description

The National Archives Netherlands have made this model for typewritten and print writings which were used in the Netherlands during the late 19th and early 20th century. For more information regarding the background of the model read this article (Dutch): https://www.nationaalarchief.nl/beleven/nieuws/klussen-aan-nieuw-tekstherkenningsmodel-transkribus-platform

Try this model

Use this modelOpen in Transkribus
Very low error rate3.5% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 3.5% 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.

Words72,170
Lines13,703
Training Pages254
Model ID48945
Centuries
19th c.20th c.