Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

ML-SUPERB

Benchmarks

Task NameDataset NameSOTA ResultTrend
Automatic Speech RecognitionML-SUPERB 10-min (Normal)
CER17.1
26
Language IdentificationML-SUPERB 10-min Normal
LID Accuracy90.2
18
Automatic Speech Recognition10-min ML-SUPERB Few-shots
ASR CER31.6
12
Automatic Speech RecognitionML-SUPERB 1hr Normal
CER14.4
10
Language IdentificationML-SUPERB 1hr Normal
Accuracy93.5
10
Automatic Speech RecognitionML-SUPERB 10-min Few-shots 1.0
ASR CER33.4
4
Language IdentificationML-SUPERB 10-min Few-shots 1.0
LID Accuracy85.8
4
Language IdentificationML-SUPERB 10-min Few-shots
LID Acc85.8
4
Showing 8 of 8 rows