muzykantov-2005 · PyLaia · Published November 2, 2024

Ostromir v1.0

Text Recognition

Description

A model trained on the Ostromir Gospels (National Library of Russia, Saint-Petersburg, ОР F.п.I.5., https://clck.ru/3EZgdR; transcription provided by the Manuscript corpus, https://clck.ru/3EZghT, Kalashnikov Izhevsk State Technical University) by Maxim Muzykantov (KISTU) for automatic transcription of Slavic uncial manuscripts from 11th and 12th centuries.

Try this model

Use this modelOpen in Transkribus
Very low error rate4.19% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 4.19% 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.

Words69,486
Lines18,690
Training Pages261
Model ID210353
Languages
Church SlavicRussian
Centuries
11th c.12th c.