Transkribus Print Multi-Language

Free Public AI Model for Handwritten Text Recognition with Transkribus

Transkribus Print Multi-Language

An extended Transkribus print model which in addition to common Antiqua and Fraktur typefaces can also decipher typewritten text, modern computer printouts, and even various unusual ‘decorative fonts’ from the 16th until the 21st century in several languages. It should be able to read historical Dutch, German, English, Finnish, French, and Swedish with good quality.

We have compared it with the similar HTR+ model and the results of the PyLaia model seem to match and in some cases surpass those of the HTR+ model. On one of our test sets for example, the new PyLaia model was 30% faster while having a CER of 1.28% compared to 1.64% of the HTR+ model. We have observed before that PyLaia seems to be doing very well on large and diverse train sets such as this.

…the swiss army knife for printed documents. Words trained: 4415716, CER on validation set: 1.60%.

Model Overview

Name:
Transkribus print 0.3
Creator:
Transkribus Team
Model ID:
36202
Century:
16th, 17th, 18th, 19th, 20th, 21st
Languages:
Dutch, English, Finnish, French, German, Swedish
Script:
Latin alphabet, Fraktur
Engine:
PyLaia
Material:
Print, Typewritten
CER on validation set:
1.6 %

Transkribus print 0.3 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, Typewritten 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 Latin alphabet, Fraktur documents into editable and searchable text.