Showing 1-3 of 3 projects
A toolkit for self-supervised speech pre-training and representation learning.
A state-of-the-art discrete acoustic codec model for audio language modeling with 40/75 tokens per second.
Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation.
Get weekly updates on trending AI coding tools and projects.