Doesn't even have to be that modern, my Ivy Bridge CPU already achieves faster t...

pantalaimon on March 30, 2023 | parent | context | favorite | on: Universal Speech Model

Doesn't even have to be that modern, my Ivy Bridge CPU already achieves faster than realtime performance - which makes me wonder if there is maybe some upstart cost for the GPU based solution and it would outperform the CPU only with longer clips.