SE-WSBO With LM

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 RecognitiononAISHELL-1
Word Error Rate (WER)· 2022-07-24
4.1
best: 0.55 (FireRedASR-AED)
SOTA
Improving Mandarin Speech Recogntion with Block-augmented Transformer arXiv:2207.11697
Speech RecognitiononAISHELL-1
Params(M)· 2022-07-24
46
best: 1100 (FireRedASR-AED)
Improving Mandarin Speech Recogntion with Block-augmented Transformer arXiv:2207.11697