Skip to content
  • Pricing
yinxuxy · PyLaia · Published October 22, 2026

Church Slavonic_PKUГ1648 1.0

Text Recognition

Description

This model was developed by a Peking University team using Slavonic Grammatica (1648), held at the Chinese National Library, as its training material. It can be used to recognize old-printed books issued by the “Московский печатный двор” (Moscow Print Yard). The model is therefore targeted at early printed Cyrillic books from this printing house, with the 1648 grammar serving as the basis for training and recognition.

Try this model

Drag an image here

Select a file...

PNG or JPG up to 10 Mb

Wolpi
AI Assistant

By uploading an image, you accept our terms and privacy policy.

Use this modelOpen in Transkribus
Low error rate6.22% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 6.22% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material. This is a larger model trained on diverse material, which generally makes it more robust across different handwriting styles. That said, larger training sets also make it harder to push the CER down further.

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.

Words84,213
Lines14,753
Training Pages672
Model ID652761
Languages
Church Slavic
Centuries
16th c.17th c.