WavLM Large

Reported on 2 benchmarks across 1 task · 1 paper

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

Audio2 results

Speech RecognitiononLibriSpeech test-clean
Word Error Rate (WER)· 2021-10-26
1.8
best: 0.985 (United Med ASR)
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing arXiv:2110.13900
Speech RecognitiononLibriSpeech test-other
Word Error Rate (WER)· 2021-10-26
3.2
best: 2.48 (SAMBA ASR)
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing arXiv:2110.13900