Transkribus Community · PyLaia · Published March 20, 2023
Early Kurrent Emperor I.
Text Recognition
Description
This model can decipher a wide range of Kurrent handwriting in german from the 16th to the early 19th century. Especially in the earlier centuries this model might work better than the usual Transkribus Kurrent model.
This is a generic model trained on a diverse dataset. Such models provide good results without the need for any extra training work. However, the best results can usually be achieved by training a special model for homogenous material, e. g. texts written by the same person or from a narrow historical period.
Curated by the Transkribus team, this model is occasionally updated with community data for continuous improvement.
Try this model
Use this modelOpen in Transkribus
Low error rate8% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 8% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material. This is a larger model trained on diverse material, which generally makes it more robust across different handwriting styles. That said, larger training sets also make it harder to push the CER down further.
Measured on the model's own validation data. Results on your documents may differ depending on handwriting style, document condition, language, and how closely your material resembles the training data.
Words6,404,094
Lines1,095,751
Training Pages29,081
Model ID50856