Conv + Transformer AM (ConvLM with Transformer Rescoring) (LS only)

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)· 2019-11-19
2.31
best: 0.985 (United Med ASR)
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures arXiv:1911.08460
Speech RecognitiononLibriSpeech test-other
Word Error Rate (WER)· 2019-11-19
5.18
best: 2.48 (SAMBA ASR)
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures arXiv:1911.08460