Mario Cossío Olavide · PyLaia · Published November 17, 2022

15th Century Spanish Gothic Hybrid Script (model C)

Text Recognition

Description

Late 15th century Spanish Gothic Hybrid script (gótica cursiva híbrida con influencia de cortesana), copied in Gipuzkoa. Based on Real Biblioteca de Palacio ms. II/793 (https://rbdigital.realbiblioteca.es/s/realbiblioteca/item/11890). Semipaleographic transcription system by the Hispanic Seminary of Medieval Studies. Trained on 9933 words, 1069 lines (24 single column bifolios). CER on Train: 0.1%, CER on Validation: 3.71%. Developed for the Lucidarios Project (https://lucidarios.hypotheses.org/), as model Lucidario C (v. 0.2) by Mario Cossío Olavide (cossio@umn.edu).

Try this model

15th Century Spanish Gothic Hybrid Script (model C)
Use this modelOpen in Transkribus
Very low error rate3.7% CER

Character Error Rate (CER) measures the percentage of characters incorrectly recognised. Lower is better. This model scored 3.7% on its validation set. As a rule of thumb, a CER below 10% is considered good for most handwritten material. This is a smaller, specialised model. It may achieve a very low CER on material similar to its training data, but could be less robust on unfamiliar handwriting or layouts.

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.

Words9,933
Lines1,069
Training Pages24
Model ID47702
Languages
Castilian