Audio Reconstruction on AudioSet
4.332ViSQOL ScoreWavTokenizer
Evaluation results
| Method | Links | |
|---|---|---|
| WavTokenizerDataset=Several, Quantizer=VQ, Frame Rate=75, Token Rate=752026.04 | 4.332 | |
| TAPFDataset=AudioSet, Quantizer=RVQ8, Frame Rate=50, Token Rate=4002026.04 | 4.308 | |
| DAC TokenizerDataset=Several, Quantizer=RVQ9, Frame Rate=31.25, Token Rate=2812026.04 | 4.304 | |
| A-V Static FusionDataset=AudioSet, Quantizer=RVQ8, Frame Rate=50, Token Rate=4002026.04 | 4.28 | |
| Speech TokenizerDataset=LibriSpeech, Quantizer=RVQ8, Frame Rate=50, Token Rate=4002026.04 | 4.129 | |
| TAPFDataset=AudioSet, Quantizer=FSQ, Frame Rate=50, Token Rate=502026.04 | 4.097 | |
| A-V Static FusionDataset=AudioSet, Quantizer=FSQ, Frame Rate=50, Token Rate=502026.04 | 3.942 |