Samuel: A Silly Speech Model

A developer trained a speech model that parrots speech using Pink Trombone, a vocal tract simulator, and released it at samuel.vvolhejn.com with code on GitHub. The model was trained using spare GPU capacity from Kyutai, an open-source AI lab, using only 1-2 GPUs from the interactive jobs partition. The developer plans to expand the blog post with training details.

← Back / Samuel: A silly speech model I trained a model that parrots speech using Pink Trombone, a silly vocal tract simulator. Try it here https://samuel.vvolhejn.com/ , or read the code here https://github.com/vvolhejn/samuel . I'm soon going to expand this blog post with information about how I trained this model. Check back soon Trained using spare GPU capacity from my work at Kyutai https://kyutai.org/ , an open-source AI lab. 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. 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 /