Extending Tower to the speech modality

UTTER - Unified Transcription and Translation for Extended Reality
Enterprise
community
AI & ML interests
Multimodality, Large Language Models, Speech Processing
Recent Activity
Organization Card
UTTER - Unified Transcription and Translation for Extended Reality - is a collaborative Research and Innovation Project funded under Horizon Europe that aims to leverage large language models to build the next generation of multimodal extended reality (XR) technologies for translation, summarization and minuting.
The consortium for UTTER consists of:
- Universiteit van Amsterdam,
- Instituto de Telecomunicações,
- University of Edinburgh,
- NAVER LABS Europe,
- Unbabel.
Collections
3
models
15

utter-project/SpireNoPseudo
Updated
•
7

utter-project/SpireNoBlocks
Updated
•
3

utter-project/SpireBase
Updated
•
568
•
3

utter-project/SpireFull
Updated
•
19

utter-project/SpireKMeans
Updated

utter-project/TowerFull
Updated
•
10

utter-project/mHuBERT-147-base-1st-iter
Feature Extraction
•
Updated
•
42
•
2

utter-project/mHuBERT-147-base-2nd-iter
Feature Extraction
•
Updated
•
177
•
3

utter-project/mHuBERT-147
Feature Extraction
•
Updated
•
9.59k
•
78

utter-project/EuroLLM-1.7B-Instruct
Text Generation
•
Updated
•
12.6k
•
70
datasets
None public yet