Compact yet powerful multilingual speech representation models based on the HuBERT architecture.
UTTER - Unified Transcription and Translation for Extended Reality
community
AI & ML interests
Multimodality, Large Language Models, Speech Processing
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.
models
7
utter-project/hutter-12-3rd-base
Updated
•
15
•
2
utter-project/EuroLLM-1.7B-Instruct
Updated
•
9.21k
•
54
utter-project/TowerSpeech
Updated
•
2
•
1
utter-project/EuroLLM-1.7B
Text Generation
•
Updated
•
4.14k
•
38
utter-project/mHuBERT-147
Feature Extraction
•
Updated
•
9.07k
•
69
utter-project/mHuBERT-147-base-1st-iter
Feature Extraction
•
Updated
•
6
•
2
utter-project/mHuBERT-147-base-2nd-iter
Feature Extraction
•
Updated
•
531
•
3
datasets
None public yet