Meta Spirit LM: Open multimodal language model that freely mixes text and speech | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Meta Spirit LM: Open multimodal language model that freely mixes text and speech (twitter.com/aiatmeta)
		13 points by anjneymidha on Oct 18, 2024 \| hide \| past \| favorite \| 4 comments

anjneymidha on Oct 18, 2024 | [–]

Blog post: https://ai.meta.com/blog/fair-news-segment-anything-2-1-meta...

lostmsu on Oct 18, 2024 | | [–]

The generated little llama story here https://speechbot.github.io/spiritlm/ has some issues, and appears to be less coherent than 3.1-8B

lostmsu on Oct 18, 2024 | | [–]

Says non-commercial when requesting access

elevenoh4 on Oct 18, 2024 | [–]

anyone hosting? want to try it

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact