Transkribus Team · PyLaia · Published August 27, 2021

Transkribus print 0.3

Text Recognition

Description

Extended Transkribus print model including typewriter, computer print outs and 'decorative fonts' (Schmuckschriften) ...the swiss army knife for printed documents

Try this model

Transkribus print 0.3
Use this modelOpen in Transkribus
Very low error rate1.6% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 1.6% 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.

Words4,415,716
Lines685,709
Training Pages8,513
Model ID36202
Languages
GermanEnglishFinnishFrenchDutchSwedish
Centuries
16th c.17th c.18th c.19th c.20th c.