Transcribing Spanish Texts from the Past: Experiments with Transkribus, Tesseract and Granite
Abstract
This article presents the experiments and results obtained by the GRESEL team in the IberLEF 2025 shared task PastReader: Transcribing Texts from the Past. Three types of experiments were conducted with the dual aim of participating in the task and enabling comparisons across different approaches. These included the use of a web-based OCR service, a traditional OCR engine, and a compact multimodal model. All experiments were run on consumer-grade hardware, which, despite lacking high-performance computing capacity, provided sufficient storage and stability. The results, while satisfactory, leave room for further improvement. Future work will focus on exploring new techniques and ideas using the Spanish-language dataset provided by the shared task, in collaboration with Biblioteca Nacional de Espa\~na (BNE).
Keywords
Cite
@article{arxiv.2507.04878,
title = {Transcribing Spanish Texts from the Past: Experiments with Transkribus, Tesseract and Granite},
author = {Yanco Amor Torterolo-Orta and Jaione Macicior-Mitxelena and Marina Miguez-Lamanuzzi and Ana García-Serrano},
journal= {arXiv preprint arXiv:2507.04878},
year = {2025}
}
Comments
This paper was written as part of a shared task organized within the 2025 edition of the Iberian Languages Evaluation Forum (IberLEF 2025), held at SEPLN 2025 in Zaragoza. This paper describes the joint participation of two teams in said competition, GRESEL1 and GRESEL2, each with an individual paper that will be published in CEUR