LLaMA-Omni
A low-latency, high-quality end-to-end speech interaction model
CommonProductchattingSpeech InteractionEnd-to-End Model
LLaMA-Omni is a low-latency, high-quality end-to-end speech interaction model built on the Llama-3.1-8B-Instruct architecture, aimed at achieving speech capabilities comparable to GPT-4o. The model supports low-latency speech interactions, generating text and speech responses simultaneously. It completed training in less than 3 days using only 4 GPUs, demonstrating its efficient training capabilities.
LLaMA-Omni Visit Over Time
Monthly Visits
521149929
Bounce Rate
35.96%
Page per Visit
6.1
Visit Duration
00:06:29
