j.schwarz · PyLaia · Published January 2, 2026

Moravian Land Records M2

Text Recognition

Description

Generic model (prototype) for Czech and German, trained on several hands from about 1550 to 1850. Material mainly from MZA Brno and SOkA Znojmo as well as from private property.

Try this model

Moravian Land Records M2
Use this modelOpen in Transkribus
Low error rate7.63% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 7.63% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material. This is a larger model trained on diverse material, which generally makes it more robust across different handwriting styles. That said, larger training sets also make it harder to push the CER down further.

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.

Words365,583
Lines71,032
Training Pages2,300
Model ID461585
Languages
CzechGermanLatin
Centuries
16th c.17th c.18th c.19th c.20th c.