Transkribus · Super Model · Published January 14, 2025
English Elder (Super Model)
Text RecognitionScholar+
Description
English Elder is a versatile super model in Transkribus for recognising handwritten and printed English texts. Trained on a comprehensive English dataset and enriched with community contributions, it excels in processing a wide range of documents, from early modern manuscripts to contemporary prints. Designed for general use, it delivers reliable performance across various English scripts and time periods.
Try this model
Use this modelOpen in Transkribus
Low error rate5.3% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 5.3% 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.
Words10,800,000
Model ID265029