kyutai-labs/
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
by kyutai Python Apache-2.0 licence 1,067 forks Created Aug 2024 View on GitHub
- Stars
- 11,508
- 38% of kyutai-labs's stars
- Rank
- #4,838
- of 851,984 repos, top 0.6%
- Up 9 places this week
- In Python
- #903
- of 173,302 repos, top 0.5%
Among 851,984 repos
10k–16k stars: 2,597 repos, including moshi
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +2 stars to reach #4,837
- Next milestone
- +26,664 stars to reach the top 0.1%
- Popular
- One of 5,762 repos with 10k+ stars
- Yearly average
- 5,072 stars a year since Aug 2024