RobustGER

Reported on 1 benchmark across 1 task · 1 paper

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

Audio1 result

Speech RecognitiononWSJ eval92
Word Error Rate (WER)· uses extra data· 2024-02-08
2.2
best: 1.3 (Speechstew 100M)
It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition arXiv:2402.05457