Vladimir Neumann (Berlin State Library) · PyLaia · Published October 30, 2024

Kirillova kniga (Church Slavonic Prints from Moscow) V1

Text Recognition

Description

The present text collection comprises printed Church Slavonic works from the Kirchenslavica Digital collection of the Berlin State Library. It enables a systematic analysis of historical texts published between 1641 and 1885, with the majority of works printed in Moscow. The collection covers a variety of genres, ranging from theological treatises to liturgical texts, thus offering a broad thematic scope. The Kirillova kniga (1885/1644) accounts for the largest share, comprising 40.47% of the entries, while the Učitelnoe evangelie (1652), at 4.94%, represents the smallest share. Medium-sized works, such as the Psaltir’ ryfmotvornym slogi (1680, Moscow) with 18.58% and the Poučenija Knigi Svjatago Efrema (1647, Moscow) with 11.78%, complement the collection. Additional texts include the Prolog, pervaja polovina (1641, Moscow) with 11.06%, the Služebnik (1655, Moscow) with 7.53%, and the Kniga o věrě edinoj istinnoj pravoslavnoj (1785, Grodno) with 7.06%, the only work in the collection not printed in Moscow. The collection is characterized by a strong focus on Moscow as the primary place of publication and presents a differentiated quantitative structure, facilitating both diachronic and synchronic studies of East Slavic written culture. (Further Information: https://slavistik-portal.de/corphub.html)

Try this model

Use this modelOpen in Transkribus
Very low error rate3.22% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 3.22% 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.

Words60,276
Lines11,662
Training Pages415
Model ID208113
Languages
Church Slavic