Already in use
A selection of research projects already working with our infrastructure — several are featured below, or will be soon.
DHInfra coordinated a loan of TU Wien's portable MISHA system to recover faded Old Serbian text on damaged charters in Cetinje — here is how the process works.
How Ferdinand Köppen used a H200 GPU to describe nearly a million video keyframes for his master thesis.
OCR post-correction with LLMs — a hands-on workshop at Universität Wien, backed by the DHInfra.at cluster.
Testing the DHInfra.at inference API on the account books of Aldersbach Abbey — open models, matched against commercial ones.
Secure model training and deployment for DH applications, scaling beyond consumer hardware.
Innovative automation for digitizing fragile historical documents, presented at "Digitise.Transform.Inspire".