Royal Danish Library · PyLaia · Published November 16, 2022
RoyalDanishLibrary_20thCentury_Py
Text Recognition
Description
A general model for Danish cursive handwriting in the 20th century.
Based on 16 different scribes.
PyLaia
CER (validation) = 3.00 %
93 epochs
580.000 words (training)
52.000 word (validation)
Originally created in November 2019 by
Jakob K. Meile & the staff at the RDL; Retrained as PyLaia in November 2022
Try this model
Use this modelOpen in Transkribus
Very low error rate3% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 3% 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.
Words580,371
Lines148,345
Training Pages3,833
Model ID47113