This is the data hub for the DiJeSt project http://dijest.net/

Supported by Rothschild Foundation Hanadiv Europe, DiJeSt is an incubator for digital humanities work in Jewish studies.

Optical character recognition (OCR), OCR correction and model training for texts printed in the Hebrew letter in the various Jewish languages. We created ground truth sets with https://transkribus.eu, where the DiJeSt model is now publicly open.

• to do: conversions between open access and open source tools to encourage flow of ground truth data ((page.xml, alto(2, 4 and more)

The data we processed and modelled is available for query and download on eLinda. We share here datasets that are in need of further processing and reconciliation.

DiJeSt Read:

• Ben Kiessling, Robin Tissot, Daniel Stoekl, https://escripta.hypotheses.org

DiJeSt Data:

• Sinai Rusinek, project leader
• Yael Netzer, DICTA, lead contributor
• Kepa J. Rodrigues, LOD consultant https://www.xplace.com/il/en/u/keparodriguez
• Oren Mishali, Lab Engineer, Technion Data and Knowledge Laboratory (TDK) http://www.cs.technion.ac.il/~omishali/