Manu McFrench, from zero to hero: impact of using a generic handwriting recognition model for smaller datasets - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Manu McFrench, from zero to hero: impact of using a generic handwriting recognition model for smaller datasets

Résumé

Long paper presentation for ADHO's annual conference on Digital Humanities (2023), discussing the importance of using generic transcription models for HTR and how to create them. We use the case of the CREMMA datasets and the Manu McFrench models as an example.
Fichier principal
Vignette du fichier
DH23___Manu_McFrench.pdf (631.95 Ko) Télécharger le fichier
chague_clerice_DH2023_Manu_McFrench.pdf (7.9 Mo) Télécharger le fichier
Licence : CC BY SA - Paternité - Partage selon les Conditions Initiales
Licence : CC BY SA - Paternité - Partage selon les Conditions Initiales

Dates et versions

hal-04094241 , version 1 (07-06-2023)

Licence

Paternité - Partage selon les Conditions Initiales

Identifiants

  • HAL Id : hal-04094241 , version 1

Citer

Alix Chagué, Thibault Clérice, Jade Norindr, Maxime Humeau, Baudoin Davoury, et al.. Manu McFrench, from zero to hero: impact of using a generic handwriting recognition model for smaller datasets. Digital Humanities 2023: Collaboration as Opportunity, Alliance of Digital Humanities Organizations; University of Graz, Jul 2023, Graz, Austria. ⟨hal-04094241⟩
92 Consultations
73 Téléchargements

Partager

Gmail Facebook X LinkedIn More