Samuel: A silly speech model - Václav Volhejn’s page

Václav Volhejn<br>I love starting new projects. Sometimes I even finish them.<br>GitHub<br>YouTube – Polylog<br>YouTube – personal<br>TikTok<br>X/Twitter<br>LinkedIn<br>Email<br>More about me

← BackI trained a model that parrots speech using Pink Trombone, a silly vocal tract simulator.

Try it here, or read the code here.

I'm soon going to expand this blog post with information about how I trained this model.<br>Check back soon!

Trained using spare GPU capacity from my work at Kyutai, an open-source AI lab.<br>To not take compute from official projects, I made sure to use only 1-2 GPUs from the partition dedicated to interactive jobs, which always has a few unused GPUs.<br>A big thank you to my colleagues for all the speech AI wisdom without which I'd have no idea how to approach this project!

← Back

Václav Volhejn<br>I love starting new projects. Sometimes I even finish them.<br>GitHub<br>YouTube – Polylog<br>YouTube – personal<br>TikTok<br>X/Twitter<br>LinkedIn<br>Email<br>More about me