Dionisio 1.0

Free Public AI Model for Handwritten Text Recognition with Transkribus

Dionisio 1.0

Prof. Vladimir Polomac of the University of Kragujevac (Serbia), has created a generic model Dionisio 1.0. for automatic text recognition of Serbian Church Slavonic books printed in the 16th century in Venice in the printery of  Božidar Vuković and his son Vincenzo.

To train the model, portions from the following Serbian Church Slavonic books were used: Prayer Book (Euchologion) (1538–1540), Psalter (1519–1520), Prayer Book (Miscellany for Travellers) (1536), Festal Menaion (1538), Prayer Book (Miscellany for Travellers) (1547) and Hieratikon (Liturgikon) (1554). Character Error Rates for the training data is 1.66% and for validation set is 2.09%.

Model Overview

Name:
Dionisio 1.0
Creator:
Vladimir Polomac
Model ID:
39359
Century:
16th
Languages:
Serbian Church Slavonic
Script:
Cyrillic alphabet
Engine:
HTR+
Material:
Print
CER on validation set:
2.09 %
Simply upload a picture and test this model

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

Dionisio 1.0 is freely available to everyone

Get started with Transkribus and use it for your own Material
You can use this model to automatically transcribe Print documents with Handwritten Text Recgnition in Transkribus. This model can be used in the Transkribus Expert Client as well as in Transkribus Lite.
This AI model was trained to automatically convert text from images of historical Cyrillic alphabet documents into editable and searchable text.