Vladimir Polomac · PyLaia · Published June 18, 2023
Macarius 1.0.
Text Recognition
Description
Prof. Vladimir Polomac (University of Kragujevac, Serbia) created the Macarius 1.0. generic model for automatic recognition of Romanian Slavonic Early Printed Books (first half of the 16th century, Church Slavonic, Cyrillic Script). The model was created on the material of Romanian Slavonic early printed books from Târgovişte printing house: the Liturgikon from 1508 and the Teatraevangelion from 1512 from the oldest printing house managed by hieromonk Macarius, as well as the Apostle from 1547 from the printing house managed by Dimitrije Ljubavić. The process of creating and evaluating the model is described in detail in the following paper: Macarius: A HTR model for Romanian Early Printed Books, Slavistica Vilnensis 68/2 (2023): 10–23. doi:10.15388/SlavViln.2022.68(2).1
Try this model
Use this modelOpen in Transkribus
Very low error rate2.7% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 2.7% 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.
Words56,815
Lines8,634
Training Pages488
Model ID52922