Skip to main content
The European High Performance Computing Joint Undertaking (EuroHPC JU)

Multimodal models for the Scandinavian languages

50,000
Awarded Resources (in node hours)
Leonardo Booster
System Partition
3 June 2024 - 2 June 2025
Allocation Period

AI Technology: Natural Language Processing, Generative Language Modeling, Deep Learning, Audio (speech recognition, speech synthesis, etc.) and Vision (image recognition, image generation, text recognition OCR, etc.

 

This project intends to train a multimodal transformer based model incorporating text, audio, and image modalities for the scandinavian languages (Swedish, Danish, Norwegian, and Icelandic) and English.

The project will build on the team's previous experience of training large language models on HPC systems.