1 result found Sort:

ictnlp
LLaMA-Omni ictnlp
117
2.0k
apache-2.0
26
LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
speech-to-text speech-to-speech speech-interaction large-language-models speech-language-model multimodal-large-language-models
Created 2024-09-10
12 commits to main branch, last one 5 days ago