Meta Spirit LM: Open multimodal language model that freely mixes text and speech (twitter.com) 13 points by anjneymidha 2y ago ↗ HN
[–] lostmsu 2y 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
5 comments
[ 7.6 ms ] story [ 134 ms ] thread