Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning
Kyutai released two open-weight 9B speech models that raise spoken GSM8K accuracy from 27.3% to 77.1% using reinforcement learning.
3
1 stories, newest first · one card per story
Kyutai released two open-weight 9B speech models that raise spoken GSM8K accuracy from 27.3% to 77.1% using reinforcement learning.
Today 1.6K readers · 2.5K views · 780 reads · all time 189K views