data2vec

Reported on 3 benchmarks across 3 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Semantic Textual SimilarityonQuora Question Pairs
Accuracy· 2022-02-07
92.4
SOTA
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language arXiv:2202.03555
Paraphrase IdentificationonQuora Question Pairs
Accuracy· 2022-02-07
92.4
SOTA
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language arXiv:2202.03555

Audio1 result

Speech RecognitiononLibriSpeech test-other
Word Error Rate (WER)· 2022-02-07
3.7
best: 2.48 (SAMBA ASR)
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language arXiv:2202.03555