Audio Reconstruction on AudioSet (16kHz Metrics)
0.268Mel-16kUniFlow-Audio
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| UniFlow-AudioFrame Rate=50, RTF=0.01672026.05 | 0.268 | 1.185 | |
| EzAudioFrame Rate=50, RTF=0.00542026.05 | 0.298 | 1.226 | |
| DashengTokenizerFrame Rate=25, RTF=0.00342026.05 | 0.37 | 1.736 | |
| Ming-UniAudioFrame Rate=50, RTF=0.00502026.05 | 0.5 | 1.949 | |
| DACFrame Rate=50, RTF=0.00432026.05 | 0.615 | 1.884 | |
| LoSATokFrame Rate=25, RTF=0.00332026.05 | 0.76 | 2.296 | |
| XY-TokenizerFrame Rate=12.5, RTF=0.00992026.05 | 1.096 | 2.795 | |
| SNACRTF=0.00192026.05 | 1.156 | 2.7 |