in

Moshi releases real-time native multi-modal model – Demo available #Moshi

Moshi - Real-Time Native Multi-Modal Model Released - Try Demo

The video introduces Moshi, an artificial intelligence model developed in just 6 months by Kyutai research lab with a team of 8. Moshi has unprecedented vocal capabilities and was created from scratch. The video also includes links for viewers to support the channel by buying coffee or getting a discount on GPU rental. It encourages viewers to become a patron and provides links to the creator’s LinkedIn, YouTube, and blog. The video is related to Kyutai and includes a link to the organization’s website. All rights are reserved by Fahd Mirza in 2021.

Source link

Source link: https://www.youtube.com/watch?v=AuXNiQvoe6g

What do you think?

Leave a Reply

GIPHY App Key not set. Please check settings

LLMs Are Stupid, Part 1 - Devin Schumacher

Devin Schumacher’s Part 1: Why LLMs Are Stupid #education

per2

More Math Hallucinations with OpenAI, exacerbated by Gemini. #mathematics