W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training
Open paper
Benchmark
Model
Rank
Results
speech-recognition-on-librispeech-test-clean
w2v-BERT XXL
#29
Word Error Rate (WER): 1.4
speech-recognition-on-librispeech-test-other
w2v-BERT XXL
#10
Word Error Rate (WER): 2.5
Rank counts only results with a code link.