wav2vec 2.0

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

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

Audio2 results

Speech RecognitiononTIMIT
Percentage error· uses extra data· 2020-06-20
8.3
SOTA
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations arXiv:2006.11477
Speech RecognitiononLibriSpeech test-other
Word Error Rate (WER)· uses extra data· 2020-06-20
4.1
best: 2.48 (SAMBA ASR)
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations arXiv:2006.11477