coidacis · PyLaia · Published August 8, 2024

19th century Greek 8.0

Text Recognition

Description

Model created by Koidaki Fotini for the needs of a PhD research project launched at AUTH and completed as part of the TALOS-AI4SSH project at UoC.

Try this model

Use this modelOpen in Transkribus
Very low error rate0.93% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 0.93% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material.

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.

Words187,561
Lines24,836
Training Pages413
Model ID148525
Languages
Greek Modern (1453-)Greek Ancient (to 1453)
Centuries
19th c.20th c.