Skip to content
blog_transkribubus-1
Dutch Text recognition models

5 AI models for transcribing letters and documents in Dutch

READ-COOP |

The Netherlands is known not only for its rich history but also for the meticulous way it records that history. With state archives in every province, not to mention the famous National Archives of the Netherlands in Amsterdam, accessing Dutch documents such as birth registers and court records is relatively easy. However, reading the handwriting in these documents is often a little trickier. The combination of older styles of handwriting, outdated terms, and phrases, plus the fact that many documents may be partially damaged or illegible makes manual transcription a time-consuming task.

Transkribus makes it much easier to read handwritten manuscripts in Dutch. © Murakami Gensui, Public domain, via Wikimedia Commons

Nowadays, though, AI can help. AI text recognition platforms such as Transkribus make it possible to automatically transcribe handwritten documents at the click of a button. You simply upload an image of the document, select an AI model on the platform, and receive an automatic transcription, which can then be edited and exported as required. Transkribus even lets you add metadata to your transcriptions, making it easier to search for named entities such as people or places.

If you want to transcribe your handwritten documents with Transkribus, here are five models that are ideal for Dutch handwriting.

 

1) The Dutchess — an all-purpose model from the National Archives and the Amsterdam City Archives

The Dutchess is ideal for any kind of Dutch handwriting. © Transkribus

If you are using our free Individual plan, then this is your go-to model for all things Dutch. Based on existing models from the National Archives and the Amsterdam City Archives, among other institutions, the Dutchess is trained on a wealth of material from the 17th to the 19th century and is ideal for use with notarial writing, chronicles, and other such documents. You can find out more about the Dutchess here.

 

2) The Dutch Demeter — our premium Super Model for transcribing Dutch handwriting

Our premium Dutch Demeter Super Model produces highly accurate transcriptions at lightning speed. © Transkribus

However, if you have upgraded to our Scholar plan, then you have access to our powerful Dutch Demeter Super Model. Using advanced transformer technology, the Dutch Demeter offers unparalleled accuracy, producing complete transcriptions with little post-editing required. It was trained on a corpus of over 18 million words from materials provided by a range of institutions in the Netherlands and has a CER of 4.9%. You can find out more about the Dutch Demeter here.

 

3) Dutch 17th century — a specialist model for documents from the 1600s

17th-century documents such as these can be transcribed instantly. © Stadsarchief Gent via Chronicling Novelty

Created by a team from the Amsterdam City Archives and the Chronicling Novelty research project, this model was trained exclusively on handwritten notarial documents from the 17th century. It includes materials from both Belgium and the Netherlands — over 1.8 million words in total. You can find out more about the Dutch 17th century model here.

 

4) Medieval Scripts - a large model for medieval texts and manuscripts

Transkribus is also capable of reading medieval manuscripts such as this devotional book. © Universiteitsbibliotheek UGent, Public domain, via Wikimedia Commons

If you work with medieval documents in Dutch, then this is the model for you. Trained on over 7 million words, it is capable of reading not just handwriting in Dutch, but also in Latin, French, and German, and can transcribe documents from the entire medieval period. You can find out more about the Medieval Scripts model here.

 

5) War Letters - a dedicated model for 20th-century handwritten letters

The NIOD is one of many Dutch institutions that transcribe their documents with Transkribus. © NIOD Institute for War, Holocaust and Genocide Studies

Created by the NIOD Institute for War, Holocaust, and Genocide Studies in Amsterdam, this unique model was trained on a collection of letters written between 1935 and 1950 by a wide range of individuals including children, soldiers, and Jewish people in hiding. It is ideal for transcribing handwritten letters in Dutch from this period. You can find out more about the War Letters model here.

 

How do I use an AI model with Transkribus?

Transkribus’ transcriptions are based on AI models. Each model has been trained to read a specific type of handwritten or printed text in a certain language, and often a certain time period or genre too.

To transcribe a document with Transkribus, you first need to upload a scan of the document and then you choose a model. There are over 200 public models available, which are all completely free to use. Transkribus will take the information stored in that model and apply it to your document, creating an instant transcription.

Sign up now for your free Transkribus account at app.transkribus.org or take a look at our First Steps video below to learn more.

If you are an archive or library and want to join the growing list of Dutch institutions using Transkribus, then set up a consultation with us and find out how Transkribus could benefit your digitisation projects.

 

Share this post