Meta Spirit LM: Open multimodal language model that freely mixes text and speech
12 points
6 hours ago
| 4 comments
| twitter.com
| HN
▲
anjneymidha
6 hours ago
[-]
Blog post: https://ai.meta.com/blog/fair-news-segment-anything-2-1-meta...
reply
▲
elevenoh4
5 hours ago
[-]
anyone hosting? want to try it
reply
▲
lostmsu
5 hours ago
[-]
The generated little llama story here https://speechbot.github.io/spiritlm/ has some issues, and appears to be less coherent than 3.1-8B
reply
▲
lostmsu
5 hours ago
[-]
Says non-commercial when requesting access
reply