BRA-E

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 RecognitiononAISHELL-1
Params(M)· 2023-03-23
8.5
best: 1100 (FireRedASR-AED)
Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition arXiv:2303.13072
Speech RecognitiononAISHELL-1
Word Error Rate (WER)· 2023-03-23
6.63
best: 0.55 (FireRedASR-AED)
Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition arXiv:2303.13072