Paraformer-large

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

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

Audio4 results

Speech RecognitiononAISHELL-2
Word Error Rate (WER)· uses extra data· 2023-05-18
2.85
SOTA
FunASR: A Fundamental End-to-End Speech Recognition Toolkit arXiv:2305.11013
Speech RecognitiononWenetSpeech
Character Error Rate (CER)· uses extra data· 2023-05-18
6.97
SOTA
FunASR: A Fundamental End-to-End Speech Recognition Toolkit arXiv:2305.11013
Speech RecognitiononAISHELL-1
Params(M)· uses extra data· 2023-05-18
220
best: 1100 (FireRedASR-AED)
SOTA
FunASR: A Fundamental End-to-End Speech Recognition Toolkit arXiv:2305.11013
Speech RecognitiononAISHELL-1
Word Error Rate (WER)· uses extra data· 2023-05-18
1.95
best: 0.55 (FireRedASR-AED)
FunASR: A Fundamental End-to-End Speech Recognition Toolkit arXiv:2305.11013