LSTM Transducer

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)· uses extra data· 2021-04-07
2.23
best: 0.985 (United Med ASR)
Librispeech Transducer Model with Internal Language Model Prior Correction arXiv:2104.03006
Speech RecognitiononLibriSpeech test-other
Word Error Rate (WER)· uses extra data· 2021-04-07
5.6
best: 2.48 (SAMBA ASR)
Librispeech Transducer Model with Internal Language Model Prior Correction arXiv:2104.03006