digitalisierung · PyLaia · Published December 16, 2024
Hans Thoma
Text Recognition
Description
Das Modell ist trainiert auf die Handschrift von Hans Thoma (1839-1924). Maler, Grafiker und Direktor der Kunsthalle Karlsruhe. Die Badische Landesbibliothek hat in einem von der Stiftung Kulturgut Baden-Württemberg geförderten Projekt 2024 und 2025 den Sammlungs- und Nachlassbestand Hans Thoma digitalisiert und mit Volltexten versehen: https://digital.blb-karlsruhe.de/Autographen/topic/view/1061273
Try this model
Use this modelOpen in Transkribus
Low error rate5.38% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 5.38% 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.
Words167,807
Lines27,691
Training Pages1,626
Model ID246709