Vast amounts of historical documents are preserved in Catalan archives, many of which have been digitized as images. The aim of our research line is to build datasets, train models, and develop tools for processing and extracting information from these historical documents, enabling more efficient exploration and analysis of archival collections.
Featured Dataverses

In order to use this feature you must have at least one published or linked dataverse.

Publish Dataverse

Are you sure you want to publish your dataverse? Once you do so it must remain published.

Publish Dataverse

This dataverse cannot be published because the dataverse it is in has not been published.

Delete Dataverse

Are you sure you want to delete your dataverse? You cannot undelete this dataverse.

Advanced Search

1 to 2 of 2 Results
AMSMB HTR model for Medieval Notarial Manuscripts
Dec 1, 2025
Berganzo-Besga, Iban; Coll Ardanuy, Mariona, 2025, "AMSMB HTR model for Medieval Notarial Manuscripts", https://dataverse.bsc.es/dataset.xhtml?persistentId=perma:BSC/AQRKOH, BSC Dataverse, V2
AMSMB HTR is a model trained using Kraken. The model uses the Tridis v1 model as base and is fine-tuned on the AMSMB HTR dataset (model named ft:v1 on the paper). Details on how the model was trained are reported in our GitLab repository and in our paper (see citation information below).
A Dataset for Handwritten Text Recognition in Medieval Notarial Charters Written on Parchment
A Dataset for Handwritten Text Recognition in Medieval Notarial Charters Written on Parchment
Jun 26, 2025
Coll Ardanuy, Mariona; Cuadrada, Coral; Sarobe, Ramon, 2025, "A Dataset for Handwritten Text Recognition in Medieval Notarial Charters Written on Parchment", https://dataverse.bsc.es/dataset.xhtml?persistentId=perma:BSC/0VB0MC, BSC Dataverse, V1, UNF:6:U0b+M2+5lwgcyjBeeZQ5nQ== [fileUNF]
We present a new dataset for the task of handwritten text recognition on medieval manuscripts, focusing on notarial charters written on parchment dating from the 13th to 15th centuries. Our dataset is comprised of 100 digitized manuscripts (3,369 lines), which have been carefully selected to represent the large variation that is present in the sour...
Add Data

Sign up or log in to create a dataverse or add a dataset.

Sign Up Log In
Share Dataverse

Share this dataverse on your favorite social media networks.

Link Dataverse
Reset Modifications

Are you sure you want to reset the selected metadata fields? If you do this, any customizations (hidden, required, optional) you have done will no longer appear.