HTR model for German manuscripts trained from several datasets

Autor: Stefan Weil
Rok vydání: 2023
Předmět:
DOI: 10.5281/zenodo.7933463
Popis: This German handwriting recognition model has been trained with ground truth from different sources. It is based on a model for printed text. Details of the training process can be found here: https://github.com/UB-Mannheim/kraken/wiki/Training-German-Handwriting
Databáze: OpenAIRE