marco.papasidero · PyLaia · Published August 2, 2024

Legende versione 3

Text Recognition

Description

This model was trained using hagiographical texts written in Italian during the 17th and 18th centuries. These texts form the basis of legends associated with Marian sanctuaries. The model was trained using an additional 71 pages that were checked by an editor.

Try this model

Use this modelOpen in Transkribus
Very low error rate1.03% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 1.03% 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.

Words35,497
Lines3,245
Training Pages71
Model ID144525
Languages
Italian
Centuries
17th c.18th c.