https://www.dybbuk.co/ · PyLaia · Published November 13, 2022
The Dybbuk for Yiddish Handwriting
Text Recognition
Description
Yiddish Handwriting model, prepared by the project team of https://www.dybbuk.co/. Ground truth data consists mainly of play manuscripts from late 19th and early 20th century written in New York and Europe. Also included are several Yiddish letters corrected by participants of Yiddish Transkribus workshop https://ingeveb.org/pedagogy/the-dybbuk-model-a-new-yiddish-handwriting-text-recognition-tool .
Try this model
Use this modelOpen in Transkribus
Very low error rate4.4% CER
Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 4.4% 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.
Words144,985
Lines19,361
Training Pages652
Model ID46159