data2vec-audio-base-100h

Papers using or citing this model 1

• data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language 1.3K citations · 2022 · International Conference on Machine Learning · arXiv

  While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general...