Zipformer+CR-CTC (no external language model)

Reported on 3 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.

Audio3 results

Speech RecognitiononLibriSpeech test-clean
Word Error Rate (WER)· 2024-10-07
2.02
best: 0.985 (United Med ASR)
CR-CTC: Consistency regularization on CTC for improved speech recognition arXiv:2410.05101
Speech RecognitiononAISHELL-1
Params(M)· 2024-10-07
66.2
best: 1100 (FireRedASR-AED)
CR-CTC: Consistency regularization on CTC for improved speech recognition arXiv:2410.05101
Speech RecognitiononAISHELL-1
Word Error Rate (WER)· 2024-10-07
4.02
best: 0.55 (FireRedASR-AED)
CR-CTC: Consistency regularization on CTC for improved speech recognition arXiv:2410.05101