w2v-BERT XXL

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 RecognitiononLibriSpeech test-other
Word Error Rate (WER)· 2021-08-07
2.5
best: 2.48 (SAMBA ASR)
SOTA
W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training arXiv:2108.06209
Speech RecognitiononLibriSpeech test-clean
Word Error Rate (WER)· uses extra data· 2021-08-07
1.4
best: 0.985 (United Med ASR)
W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training arXiv:2108.06209