hogne.sandvik · PyLaia · Published November 12, 2025
NorMed
Text Recognition
Description
The model is trained on notes taken down by medical students attending the lectures of professor Sørenssen, who taught pathology and therapy during the first years of the University of Oslo. The manuscripts, located in the collection at the National Library of Norway, were written during the years 1820-1836. Gothic handwritten texts from four different students were used in the training process.
Try this model
Use this modelOpen in Transkribus
Very low error rate3.01% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 3.01% 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.
Words70,635
Lines11,362
Training Pages530
Model ID431685