AI Roundup 06/15-> 06/22/2023

Meta's AI model for replicating voices, a 13B open source permissively licensed LLaMA reproduction, and Google's method for trying on clothes without actually wearing them

1. Meta unveils Voicebox - an AI model capable of replicating human voices and generating synthetic voices from text prompts (Meta AI)

   

2. Berkeley releases OpenLLaMA 13B - a permissively licensed open source reproduction of Meta AI’s 13B trained on the RedPajama dataset (Github repo)