meetween/Llama-speechlmm-1.0-s
Feature Extraction
•
2B
•
Updated
•
3
SpeechLMM v1
1st generation of SpeechLMM models, capable of ingesting video, audio and text and generate text as output. From the Meetween consortium (meetween.eu)
-
-
meetween/Llama-speechlmm-1.0-m
Feature Extraction • 4B • Updated • 4 -
meetween/Llama-speechlmm-1.0-l
Feature Extraction • 8B • Updated • 4 -
meetween/Llama-speechlmm-1.0-xl
Feature Extraction • 1B • Updated • 16 -
meetween/Llama-speechlmm-1.0-l-ASR
0.6B • Updated • 3 -
meetween/Llama-speechlmm-1.0-l-ST
Translation • 9B • Updated • 5 -
meetween/Llama-speechlmm-1.0-l-MT
Translation • 9B • Updated • 4 -
meetween/Llama-speechlmm-1.0-l-SLU
9B • Updated • 1 -
meetween/Llama-speechlmm-1.0-l-LIPREAD
Other • 9B • Updated • 17 -
meetween/Llama-speechlmm-1.0-l-SQA
Translation • 9B • Updated • 3 -
meetween/Llama-speechlmm-1.0-l-SSUM
9B • Updated • 1 -
meetween/Llama-speechlmm-1.0-l-TSUM
9B • Updated • 2