Spanish Gothic Incunabula (HSMS)

This model is trained to recognize the Gothic typefaces used in Castilian incunabula. It is based on twenty books printed in the workshops of Stanislao Polono & Meinardo Ungut (Seville: RGP, CNB, JOS, CLS, SPO), Fadrique de Basel (Burgos: LES, AYL, C87, AXP), Pablo Hurus (Zaragoza: ERI, APL, SVH, ACM, VTS, LIM), Cuatro Compañeros (Seville: CAR), Juan de Burgos (Burgos: AUG, BMP), Pedro Hagenbach (Toledo: CUR), and Guillén de Brocar (Pamplona: GEN), all printed between 1487 and 1499. For the correspondence between these acronyms (developed by the Hispanic Seminary of Medieval Studies) and the actual works and copies used, see Fradejas Rueda & Cossío Olavide (2025).

The samples from these twenty editions include ten folios (verso-recto) per copy, transcribed according to the HSMS transcription system (http://hispanicseminary.org/manual-en.htm). This means that all abbreviations are expanded and enclosed between < > signs, and superscript letters are followed by a grave accent. The model was trained over 207 epochs on a dataset of 180.152 words and 24.061 lines (mostly from 200 double-column folio openings). The training CER is 0.2%, with a validation CER of 0.77% and a WER of 3.21%.

Developed within the project 7PartidasDigital (PID2020-112621GB-I00; funded by MCIN/AEI/ 10.13039/501100011033) by José Manuel Fradejas Rueda.