+ National Archives releases first version of a Dutch handwriting model

The digitisation team around Liesbeth Keyser from the National Archives in the Netherlands is working hard on creating training data for their collections in order to prepare HTR processing on a large scale. As a first result a model based on 475.769 words is now made available for Transkribus users. The model shows a Character Error Rate of 7.48% on the training set and 6.15% on the validation set. It is based on the careful transcription of dozens of different handwritings and comprises scans from the Incoming Documents from the Dutch East India Company (Overgekomen Brieven en Papieren van de VOC) of the National Archives of the Netherlands and of 19th century Notarial deeds from the Noord-Hollands archief.  The model is named: NAN/NHA_GT_M3+ Enjoy!

 

 

SHARE THIS ARTICLE

Recent Posts

September 19, 2023
Transkribus
We are thrilled to announce the September 2023 release of the Transkribus web app. After the successful switch to the ...
August 30, 2023
News, Transkribus
Today, the new Transkribus web app is officially launched!  Transkribus has always worked towards simplifying the digitasion and transcription of ...
August 21, 2023
Transkribus User Conference
The Transkribus User Conference 24 (15 & 16 February 2024, Innsbruck) invites stakeholders, users, scholars, and enthusiasts to explore the ...