W2V2-B-LS960 (+ TED-LIUM 3 LM)

Reported on 4 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.

Audio4 results

Speech RecognitiononSLUE
VoxCeleb (Dev)· 2021-11-19
13.2
best: 29.9 (W2V2-B-VP100K )
SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech arXiv:2111.10367
Speech RecognitiononSLUE
VoxCeleb (Test)· 2021-11-19
15.8
best: 33.4 (W2V2-B-VP100K )
SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech arXiv:2111.10367
Speech RecognitiononSLUE
VoxPopuli (Dev)· 2021-11-19
12
best: 21.6 (W2V2-B-VP100K )
SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech arXiv:2111.10367
Speech RecognitiononSLUE
VoxPopuli (Test)· 2021-11-19
12.2
best: 22.4 (W2V2-B-VP100K )
SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech arXiv:2111.10367