Speaker Identification on VoxCeleb
94.8AccuracyAudioMAE
Evaluation Results
| Method | Links | |
|---|---|---|
| AudioMAEParams=85M, GFLOPs=42.4, RTF=0.2442026.03 | 94.8 | |
| HEARParams=15M, GFLOPs=9.47, RTF=0.0952026.03 | 87.9 | |
| HuBERTParams=94M, GFLOPs=69.6, RTF=0.510, Protocol=frozen pre-trained model2026.03 | 81.4 | |
| wav2vec 2.0Params=94M, GFLOPs=69.6, RTF=0.510, Protocol=frozen pre-trained model2026.03 | 75.1 | |
| SSASTParams=85M, GFLOPs=42.4, RTF=0.2442026.03 | 64.2 |