Paraformer

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

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

Audio3 results

Speech RecognitiononAISHELL-2
Word Error Rate (WER)· 2023-05-18
5.73
best: 2.85 (Paraformer-large)
SOTA
FunASR: A Fundamental End-to-End Speech Recognition Toolkit arXiv:2305.11013
Speech RecognitiononAISHELL-1
Params(M)· 2023-05-18
46.3
best: 1100 (FireRedASR-AED)
FunASR: A Fundamental End-to-End Speech Recognition Toolkit arXiv:2305.11013
Speech RecognitiononAISHELL-1
Word Error Rate (WER)· 2023-05-18
4.95
best: 0.55 (FireRedASR-AED)
FunASR: A Fundamental End-to-End Speech Recognition Toolkit arXiv:2305.11013