Already got to know one of our biggest models in Transkribus? That is the German_Kurrent_17th-18th model by the University of Greifswald. Different kinds of texts have been part of the training to do justice to its nickname “The Kurrent Jack of all Trades”. Most of the trained manuscripts are part of the council minutes of the University of Greifswald, the assessor votes of the Wismar High Court, the minutes of the Pomeranian government of Stralsund, the responsa of the Greifswald Law Faculty and other archival holdings such as private letter collections. The training data primarily consists of documents from the 17th-18th century and a couple of pages from the 19th century. The model has a training set of more than 1 840 000 words (honestly!) and a Character Error Rate on the Validation Set of 5.5%. It is a good choice to get a reasonable transcription for any Kurrent-script you have or if you need a stable base model for 17th-19th century German writings.
Many thanks to the University of Greifswald for this powerful giant!
