Transkribus · Super Model · Published April 5, 2023
The Text Titan I (Super Model)
Description
This is the first generation of the Transkribus Super Models containing German, English, Dutch, French, Finnish and Swedish training material.
Please note that Super Models cannot be used as base models for custom model training due to their extensive amount of data.
Try this model
Use this modelOpen in Transkribus
Very low error rate2.95% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 2.95% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material. Super Models are trained on very large and diverse datasets, making them robust across a wide range of handwriting styles and languages. Because of this diversity, a low CER on the validation set is a strong indicator of general-purpose quality.
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.
Lines4,905,050
Model ID51170