wav2vec 2.0 Large-10h-LV-60k

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

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

Audio2 results

Speech RecognitiononLibri-Light test-other
Word Error Rate (WER)· 2020-06-20
5
SOTA
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations arXiv:2006.11477
Speech RecognitiononLibri-Light test-clean
Word Error Rate (WER)· 2020-06-20
2.5
SOTA
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations arXiv:2006.11477