Jasper DR 10x5

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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

Audio4 results

Speech RecognitiononHub5'00 SwitchBoard
CallHome· 2019-04-05
16.2
best: 18.4 (CTC-CRF)
SOTA
Jasper: An End-to-End Convolutional Neural Acoustic Model arXiv:1904.03288
Speech RecognitiononHub5'00 SwitchBoard
SwitchBoard· 2019-04-05
7.8
best: 9.7 (CTC-CRF)
SOTA
Jasper: An End-to-End Convolutional Neural Acoustic Model arXiv:1904.03288
Speech RecognitiononLibriSpeech test-clean
Word Error Rate (WER)· 2019-04-05
2.95
best: 0.985 (United Med ASR)
SOTA
Jasper: An End-to-End Convolutional Neural Acoustic Model arXiv:1904.03288
Speech RecognitiononLibriSpeech test-other
Word Error Rate (WER)· 2019-04-05
8.79
best: 2.48 (SAMBA ASR)
SOTA
Jasper: An End-to-End Convolutional Neural Acoustic Model arXiv:1904.03288