Model
SpidR 2.0
A self-supervised speech encoder that induces high-quality discrete speech units at multiple levels through differentiable prediction heads. It serves as the front-end encoder of GSLM2.
Timeline (last 90 days)
Nov 3
GSLM2's encoder is named SpidR 2.0, which uses self-supervised learning and introduces a differentiable prediction head to induce high-quality discrete units at multiple levels.
Unverified50%