Model Title

Here comes a short description of the model

See facts Try it out

Model facts

Creator(s)

Name Name Name

Language(s)

German, Dutch, English

Centuries

15th, 16th, 17th

CER on Validation Set

5.12%

Size (Nr. of Words)

12 012 111

Model ID

124921

About this Model

There are a number of old German Scripts that were used in the German speaking World between the 16th and 20th century. On the one hand, there were a number of handwritings including Kurrent Script, Sütterlin, Offenbacher Script. But there were also some printed Scrpits such as Fraktur or Antiqua.

With the help of Transkribus accessing and searching a large number of historical documents – written in old German Scripts – is today possible. By using one of the public models or a own model, thousands of historical documents can be automatically converted into text.

This new public model for the recognition of medieval Latin has been released thanks to a collaboration between the Bentham Project of the University College London and the DEEDS (Documents of Early England Data Set) Project of the University of Toronto. What is special: Transkribus can now read the peculiar type of handwritten medieval Latin found in 12th- to 15th- century legal manuscripts. This is “peculiar” because legal Latin is full of idiosyncratic abbreviations and random word hyphenations. It has been created with material from the DEEDS Project at the University of Toronto, established by Professor Michael Gervers in 1975, and later expanded with material from the St Frideswide and Eynsham Abby cartularies, held by Christ Church College, Oxford. More than 140 000 words have been trained and the CER on the Validation Set is 1.71%.

Contact: Chris Riley: c.riley@ucl.ac.uk.

Try it out

Model-ID needs to be dynamic for this component

{Transkribus German Kurrent M2} is freely available to everyone

You can use this model to automatically transcribe Handwritten documents with Handwritten Text Recgnition in Transkribus.