Philipp Wasserscheidt · PyLaia · Published August 15, 2023

Montenegrin/Serbian Cyrillic 1.0

Text Recognition

Description

This is the first version of a model for printed Serbian / Montenegrin Cyrillic, trained and curated by Philipp Wasserscheidt at Humboldt-Universität zu Berlin. The data consists of a selection of prints from the late 19th century up to contemporary prints. This model will be updated with for continuous improvement.

Try this model

Use this modelOpen in Transkribus
Very low error rate0.2% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 0.2% 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.

Words38,223
Lines4,813
Training Pages76
Model ID54383
Languages
Serbian
Centuries
19th c.20th c.21st c.