Audio Reconstruction on AudioSet (test)
0.32Mel Distance (16kHz)DashengTokenizer
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| DashengTokenizerFramerate=252026.02 | 0.32 | — | — | 1.585 | |
| UniFlow-AudioFramerate=502026.02 | 0.321 | — | — | 1.385 | |
| EzAudioFramerate=502026.02 | 0.349 | — | — | 1.434 | |
| BigVGANUnified=true, SR=44.1, Token rate category=Vocoder2026.01 | 0.363 | 0.417 | 1.713 | 1.683 | |
| MingTok-AudioFramerate=502026.02 | 0.462 | — | — | 1.768 | |
| DACUnified=true, TPS=900, kbps=9, Nq=9, SR=44.1, Token rate category=> 1002026.01 | 0.625 | 0.654 | 1.958 | 1.842 | |
| DACFramerate=502026.02 | 0.664 | — | — | 1.986 | |
| UniSRCodec-LUnified=true, TPS=176, kbps=2.29, Nq=1, SR=44.1, Token rate category=> 1002026.01 | 0.692 | 0.729 | 2.049 | 2.093 | |
| SNACUnified=true, TPS=240, kbps=2.88, Nq=4, SR=44.1, Token rate category=> 1002026.01 | 0.863 | 0.828 | 2.145 | 2.234 | |
| MelCapUnified=true, TPS=260, kbps=3.4, Nq=1, SR=44.1, Token rate category=> 1002026.01 | 0.873 | 0.817 | 2.229 | 2.409 | |
| EncodecUnified=true, TPS=600, kbps=6, Nq=8, SR=24, Token rate category=> 1002026.01 | 0.889 | 1.315 | 5.03 | 2.271 | |
| UniSRCodec-BUnified=true, TPS=40, kbps=0.52, Nq=1, SR=44.1, Token rate category=≤ 1002026.01 | 0.9 | 0.904 | 2.25 | 2.33 | |
| XY-TokenizerFramerate=12.52026.02 | 0.901 | — | — | 2.361 | |
| UniCodecUnified=true, TPS=75, kbps=1.3, Nq=1, SR=24, Token rate category=≤ 1002026.01 | 0.903 | 1.376 | 5.169 | 2.401 | |
| WT-MAUnified=false, TPS=75, kbps=0.9, Nq=1, SR=24, Token rate category=≤ 1002026.01 | 0.985 | 1.396 | 5.132 | 2.453 | |
| EncodecUnified=true, TPS=300, kbps=3, Nq=4, SR=24, Token rate category=> 1002026.01 | 1.017 | 1.413 | 5.134 | 2.448 | |
| WT-SpeechUnified=false, TPS=75, kbps=0.9, Nq=1, SR=24, Token rate category=≤ 1002026.01 | 1.026 | 1.393 | 5.179 | 2.572 | |
| WT-UnifiedUnified=true, TPS=40, kbps=0.48, Nq=1, SR=24, Token rate category=≤ 1002026.01 | 1.13 | 1.505 | 5.242 | 2.634 | |
| SNAC2026.02 | 1.195 | — | — | 2.69 | |
| XCodec 2.0Framerate=502026.02 | 1.253 | — | — | 2.925 | |
| DACUnified=true, TPS=100, kbps=1, Nq=1, SR=44.1, Token rate category=≤ 1002026.01 | 1.282 | 1.187 | 2.588 | 2.752 | |
| BigCodecUnified=false, TPS=80, kbps=1.04, Nq=1, SR=16, Token rate category=≤ 1002026.01 | 1.366 | 2.25 | 7.336 | 3.024 | |
| TAAEUnified=false, TPS=50, kbps=0.7, Nq=1, SR=16, Token rate category=≤ 1002026.01 | 2.385 | 2.999 | 7.896 | 4.314 |