Audio Reconstruction on AudioSet (eval)
0.382Mel DistanceUniCodec
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| UniCodecUnified=true, TPS=752025.02 | 0.382 | 2.1065 | — | — | — | — | |
| Wavtokenizer (music/audio)Unified=false, TPS=752025.02 | 0.4536 | 2.1871 | — | — | — | — | |
| DACUnified=true, TPS=6002025.02 | 0.4581 | 2.1378 | — | — | — | — | |
| Wavtokenizer (unified)Unified=true, TPS=752025.02 | 0.5193 | 2.3727 | — | — | — | — | |
| Wavtokenizer (speech)Unified=false, TPS=752025.02 | 0.599 | 2.5479 | — | — | — | — | |
| DACbps=6000, Frame rate=75, NVQ=82026.02 | 0.65 | 1.97 | — | — | — | — | |
| DACbps=6000, Frame rate=75, NVQ=82026.03 | 0.65 | 1.97 | — | — | — | — | |
| MiMo-Audio-Tokenizerbps=3650, Frame rate=25, NVQ=202026.02 | 0.66 | 2.17 | — | — | — | — | |
| MiMo-Audio-Tokenizerbps=3650, Frame rate=25, NVQ=202026.03 | 0.66 | 2.17 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=4000, Frame rate=12.5, NVQ=322026.02 | 0.68 | 1.96 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=4000, Frame rate=12.5, NVQ=322026.03 | 0.68 | 1.96 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=3000, Frame rate=12.5, NVQ=242026.02 | 0.69 | 1.98 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=3000, Frame rate=12.5, NVQ=242026.03 | 0.69 | 1.98 | — | — | — | — | |
| MiMo-Audio-Tokenizerbps=2250, Frame rate=25, NVQ=122026.02 | 0.7 | 2.21 | — | — | — | — | |
| MiMo-Audio-Tokenizerbps=2250, Frame rate=25, NVQ=122026.03 | 0.7 | 2.21 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=2000, Frame rate=12.5, NVQ=162026.02 | 0.73 | 2.03 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=2000, Frame rate=12.5, NVQ=162026.03 | 0.73 | 2.03 | — | — | — | — | |
| Higgs-Audio-Tokenizerbps=2000, Frame rate=25, NVQ=82026.02 | 0.74 | 2.07 | — | — | — | — | |
| Higgs-Audio-Tokenizerbps=2000, Frame rate=25, NVQ=82026.03 | 0.74 | 2.07 | — | — | — | — | |
| EncodecUnified=true, TPS=6002025.02 | 0.7601 | 2.6273 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=1500, Frame rate=12.5, NVQ=122026.02 | 0.77 | 2.08 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=1500, Frame rate=12.5, NVQ=122026.03 | 0.77 | 2.08 | — | — | — | — | |
| MiMo-Audio-Tokenizerbps=850, Frame rate=25, NVQ=42026.02 | 0.82 | 2.33 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=1000, Frame rate=12.5, NVQ=82026.02 | 0.82 | 2.16 | — | — | — | — | |
| MiMo-Audio-Tokenizerbps=850, Frame rate=25, NVQ=42026.03 | 0.82 | 2.33 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=1000, Frame rate=12.5, NVQ=82026.03 | 0.82 | 2.16 | — | — | — | — | |
| OmniCodec-32LCodebook Size=2048, Bitrate (bps)=4400, TPS=12.5×322026.03 | 0.82 | — | 1.89 | 2.6 | 0.66 | 2.74 | |
| Higgs-Audio-Tokenizerbps=1000, Frame rate=25, NVQ=42026.02 | 0.83 | 2.2 | — | — | — | — | |
| Higgs-Audio-Tokenizerbps=1000, Frame rate=25, NVQ=42026.03 | 0.83 | 2.2 | — | — | — | — | |
| MimiUnified=true, TPS=1002025.02 | 0.8406 | 2.6639 | — | — | — | — | |
| OmniCodec-16LCodebook Size=2048, Bitrate (bps)=2200, TPS=12.5×162026.03 | 0.85 | — | 1.75 | 2.44 | 0.61 | 3.04 | |
| MOSS-Audio-Tokenizerbps=750, Frame rate=12.5, NVQ=62026.02 | 0.86 | 2.21 | — | — | — | — | |
| DACbps=3000, Frame rate=75, NVQ=42026.02 | 0.86 | 2.23 | — | — | — | — | |
| MOSS-Audio-Tokenizerbps=750, Frame rate=12.5, NVQ=62026.03 | 0.86 | 2.21 | — | — | — | — | |
| DACbps=3000, Frame rate=75, NVQ=42026.03 | 0.86 | 2.23 | — | — | — | — | |
| X-Codec-8LCodebook Size=1024, Bitrate (bps)=4000, TPS=50×82026.03 | 0.88 | — | 2.07 | 2.72 | 0.65 | 4.05 | |
| OmniCodec-F-32LCodebook Size=2048, Bitrate (bps)=2200, TPS=6.25×322026.03 | 0.88 | — | 1.61 | 2.28 | 0.58 | 3.26 | |
| OmniCodec-8LCodebook Size=2048, Bitrate (bps)=1100, TPS=12.5×82026.03 | 0.9 | — | 1.55 | 2.16 | 0.52 | 3.5 | |
| OmniCodec-F-16LCodebook Size=2048, Bitrate (bps)=1100, TPS=6.25×162026.03 | 0.9 | — | 1.49 | 2.13 | 0.5 | 3.61 | |
| Encodecbps=4500, Frame rate=75, NVQ=62026.02 | 0.91 | 2.33 | — | — | — | — | |
| Encodecbps=4500, Frame rate=75, NVQ=62026.03 | 0.91 | 2.33 | — | — | — | — | |
| UniCodecCodebook Size=16384, Bitrate (bps)=1050, TPS=752026.03 | 0.96 | — | 1.59 | 2.15 | 0.49 | 4.11 | |
| Mimibps=4400, Frame rate=12.5, NVQ=322026.02 | 1.02 | 2.34 | — | — | — | — | |
| Mimibps=4400, Frame rate=12.5, NVQ=322026.03 | 1.02 | 2.34 | — | — | — | — | |
| Mimibps=2475, Frame rate=12.5, NVQ=182026.02 | 1.1 | 2.45 | — | — | — | — | |
| Mimibps=2475, Frame rate=12.5, NVQ=182026.03 | 1.1 | 2.45 | — | — | — | — | |
| WavTokenizerCodebook Size=4096, Bitrate (bps)=480, TPS=402026.03 | 1.1 | — | 1.35 | 1.77 | 0.36 | 5.08 | |
| H-Codec-2.0 (Large)BPS=20002025.12 | 1.1125 | 0.3915 | — | — | — | — | |
| Encodecbps=1500, Frame rate=75, NVQ=22026.02 | 1.12 | 2.6 | — | — | — | — | |
| Encodecbps=1500, Frame rate=75, NVQ=22026.03 | 1.12 | 2.6 | — | — | — | — | |
| Mimi codec-16LCodebook Size=2048, Bitrate (bps)=2200, TPS=12.5×162026.03 | 1.14 | — | 1.71 | 2.39 | 0.6 | 4.06 | |
| H-Codec-1.0BPS=20002025.12 | 1.2312 | 0.4023 | — | — | — | — | |
| Mimibps=1100, Frame rate=12.5, NVQ=82026.02 | 1.24 | 2.62 | — | — | — | — | |
| Mimibps=1100, Frame rate=12.5, NVQ=82026.03 | 1.24 | 2.62 | — | — | — | — | |
| AUVCodebook Size=20480, Bitrate (bps)=716, TPS=502026.03 | 1.26 | — | 1.54 | 2.13 | 0.47 | 4.37 | |
| H-Codec-2.0 (Small)BPS=20002025.12 | 1.3542 | 0.4218 | — | — | — | — | |
| X-CodecBPS=20002025.12 | 1.5073 | 0.4193 | — | — | — | — | |
| UniCodecBPS=9002025.12 | 1.5403 | 0.476 | — | — | — | — | |
| DACUnified=false, TPS=752025.02 | 1.7063 | 5.2923 | — | — | — | — | |
| BigCodecUnified=false, TPS=802025.02 | 1.8632 | 5.6171 | — | — | — | — | |
| WavTokenizerBPS=4802025.12 | 1.8912 | 0.5201 | — | — | — | — | |
| DACBPS=20002025.12 | 1.9054 | 0.5164 | — | — | — | — | |
| TAAEUnified=false, TPS=502025.02 | 1.9335 | 5.2897 | — | — | — | — |