Speech Reconstruction on LibriTTS (test-other)
4.17UTMOSCleanCodec@12.5
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CleanCodec@12.5Token Rate (t/s)=12.52026.06 | 4.17 | — | — | — | — | 5.7 | — | 3.2 | 0.84 | 21.73 | 0.44 | |
| CleanCodec@31.25Token Rate (t/s)=31.252026.06 | 4.1 | — | — | — | — | 3.6 | — | 1.9 | 0.87 | 22.12 | 0.33 | |
| KanadeToken Rate (t/s)=12.52026.06 | 4.1 | — | — | — | — | 8.2 | — | 4.5 | 0.64 | 23.77 | 0.59 | |
| Qwen3Token Rate (t/s)=2002026.06 | 4.09 | — | — | — | — | 2.6 | — | 1.4 | 0.9 | 27.85 | 0.29 | |
| BiCodecToken Rate (t/s)=502026.06 | 4.07 | — | — | — | — | 6.2 | — | 3.4 | 0.77 | 26.14 | 0.62 | |
| CleanCodec@62.5Token Rate (t/s)=62.52026.06 | 4.06 | — | — | — | — | 2.7 | — | 1.6 | 0.89 | 22.83 | 0.29 | |
| FocalCodecToken Rate (t/s)=12.52026.06 | 4.05 | — | — | — | — | 16.8 | — | 9.7 | 0.42 | 25.25 | 0.79 | |
| GTToken Rate (t/s)=–2026.06 | 4.01 | — | — | — | — | 0 | — | 0 | 1 | 24.44 | 0 | |
| XCodec2Token Rate (t/s)=502026.06 | 4.01 | — | — | — | — | 5.4 | — | 3.1 | 0.75 | 23.47 | 0.4 | |
| SylberBitrate (Hz)=4.222026.01 | 3.91 | 1.13 | 0.72 | — | — | 13.29 | 0.71 | — | — | — | — | |
| Qwen3Token Rate (t/s)=1002026.06 | 3.73 | — | — | — | — | 4.7 | — | 2.5 | 0.72 | 20.2 | 0.38 | |
| TAAEUnified=true, DR=320, TPF=2, TPS=502025.02 | 3.7136 | 1.7539 | 0.838 | 0.8994 | — | — | — | — | — | — | — | |
| MimiToken Rate (t/s)=1002026.06 | 3.63 | — | — | — | — | 7.5 | — | 4.4 | 0.7 | 17.21 | 0.56 | |
| WavTokenizerToken Rate (t/s)=402026.06 | 3.63 | — | — | — | — | 19.1 | — | 11.5 | 0.61 | 20.94 | 0.47 | |
| UniCodecUnified=true, DR=320, TPF=1, TPS=752025.02 | 3.58 | 2.2749 | 0.9095 | 0.9109 | — | — | — | — | — | — | — | |
| BigCodecUnified=false, DR=200, TPF=1, TPS=802025.02 | 3.5453 | 2.3817 | 0.9094 | 0.9237 | — | — | — | — | — | — | — | |
| Sylber 2.0Bitrate (Hz)=5.812026.01 | 3.54 | 1.89 | 0.87 | — | — | 8.58 | 0.91 | — | — | — | — | |
| Q2D2Bandwidth=1kbps, Nq=1, token/s=752025.12 | 3.5383 | 2.2224 | 0.8908 | — | 0.9199 | — | — | — | — | — | — | |
| Q2D2Bandwidth=3.3kbps, Nq=1, token/s=1662025.12 | 3.5072 | 3.096 | 0.9339 | — | 0.9531 | — | — | — | — | — | — | |
| Ground Truth2025.02 | 3.4831 | — | — | — | — | — | — | — | — | — | — | |
| GT2025.12 | 3.4831 | — | — | — | — | — | — | — | — | — | — | |
| FACodecBitrate (Hz)=802026.01 | 3.48 | 2.61 | 0.93 | — | — | 7.14 | 0.96 | — | — | — | — | |
| SACodecParams [M]=75.17, Token Rate=75, Codebook Size=1000 / 1024, Q=2, Bitrate [kbps]=1.52025.12 | 3.4786 | 2.4016 | 0.904 | 0.9273 | — | — | — | — | — | — | — | |
| Q2D2Bandwidth=6.9kbps, Nq=1, token/s=3332025.12 | 3.4481 | 3.4595 | 0.9464 | — | 0.9712 | — | — | — | — | — | — | |
| WavTokenizerParams [M]=80.55, Token Rate=75, Codebook Size=4096, Q=1, Bitrate [kbps]=0.92025.12 | 3.4315 | 2.2705 | 0.9173 | 0.8907 | — | — | — | — | — | — | — | |
| Wavtokenizer (speech)Unified=false, DR=320, TPF=1, TPS=752025.02 | 3.4312 | 2.2614 | 0.8907 | 0.9172 | — | — | — | — | — | — | — | |
| WavTokenizerBandwidth=0.9kbps, Nq=1, token/s=752025.12 | 3.4312 | 2.2614 | 0.8907 | — | 0.9172 | — | — | — | — | — | — | |
| DACBitrate (Hz)=86.12026.01 | 3.4 | 4.43 | 0.99 | — | — | 5.99 | 1 | — | — | — | — | |
| DACUnified=false, DR=48.9, TPF=9, TPS=9002025.02 | 3.3566 | 3.7595 | 0.9576 | 0.9696 | — | — | — | — | — | — | — | |
| DACBandwidth=9.0kbps, Nq=9, token/s=9002025.12 | 3.3566 | 3.7595 | 0.9576 | — | 0.9696 | — | — | — | — | — | — | |
| MimiBitrate (Hz)=12.52026.01 | 3.33 | 3.25 | 0.95 | — | — | 7.06 | 0.97 | — | — | — | — | |
| HiFi-CodecBandwidth=3.0kbps, Nq=4, token/s=3002025.12 | 3.3034 | 2.6083 | 0.9166 | — | 0.9318 | — | — | — | — | — | — | |
| SpeechTokenizerUnified=false, DR=40, TPF=8, TPS=6002025.02 | 3.2851 | 2.3269 | 0.8811 | 0.9205 | — | — | — | — | — | — | — | |
| SpeechTokenizerParams [M]=103.68, Token Rate=50, Codebook Size=1024, Q=8, Bitrate [kbps]=42025.12 | 3.2851 | 2.3269 | 0.8811 | 0.9205 | — | — | — | — | — | — | — | |
| SpeechTokenizerBandwidth=6.0kbps, Nq=8, token/s=6002025.12 | 3.2851 | 2.3269 | 0.8811 | — | 0.9205 | — | — | — | — | — | — | |
| SpeechTokenizerBitrate (Hz)=502026.01 | 3.28 | 2.41 | 0.9 | — | — | 7.81 | 0.95 | — | — | — | — | |
| VocosBandwidth=6.0kbps, Nq=8, token/s=6002025.12 | 3.1956 | 2.559 | 0.9209 | — | 0.9202 | — | — | — | — | — | — | |
| DACParams [M]=74.71, Token Rate=75, Codebook Size=1024, Q=8, Bitrate [kbps]=62025.12 | 3.1338 | 3.3429 | 0.9402 | 0.9598 | — | — | — | — | — | — | — | |
| Wavtokenizer (unified)Unified=true, DR=320, TPF=1, TPS=752025.02 | 3.082 | 1.6649 | 0.8312 | 0.8874 | — | — | — | — | — | — | — | |
| WavTokenizerBitrate (Hz)=402026.01 | 3.08 | 1.69 | 0.84 | — | — | 31.04 | 0.87 | — | — | — | — | |
| HiFi-CodecBandwidth=4.0kbps, Nq=4, token/s=4002025.12 | 3.075 | 2.5536 | 0.9126 | — | 0.9387 | — | — | — | — | — | — | |
| MimiUnified=true, DR=240, TPF=8, TPS=1002025.02 | 3.0608 | 2.0952 | 0.8816 | 0.8875 | — | — | — | — | — | — | — | |
| VocosBandwidth=3.0kbps, Nq=4, token/s=3002025.12 | 3.0558 | 2.1933 | 0.8967 | — | 0.9051 | — | — | — | — | — | — | |
| WavTokenizerBandwidth=0.5kbps, Nq=1, token/s=402025.12 | 3.0545 | 1.6622 | 0.8336 | — | 0.8953 | — | — | — | — | — | — | |
| SpeechTokenizerBandwidth=3.0kbps, Nq=4, token/s=3002025.12 | 3.0183 | 1.7373 | 0.8371 | — | 0.8907 | — | — | — | — | — | — | |
| DACBandwidth=4.0kbps, Nq=4, token/s=4002025.12 | 2.9448 | 2.5948 | 0.9083 | — | 0.9404 | — | — | — | — | — | — | |
| FACodecParams [M]=374.49, Token Rate=80, Codebook Size=1024, Q=6, Bitrate [kbps]=4.82025.12 | 2.9302 | 2.0321 | 0.8832 | 0.908 | — | — | — | — | — | — | — | |
| EncodecUnified=true, DR=40, TPF=8, TPS=6002025.02 | 2.6568 | 2.6818 | 0.9241 | 0.9338 | — | — | — | — | — | — | — | |
| EncodecParams [M]=14.85, Token Rate=75, Codebook Size=1024, Q=8, Bitrate [kbps]=62025.12 | 2.6568 | 2.6818 | 0.9241 | 0.9338 | — | — | — | — | — | — | — | |
| EncodecBandwidth=6.0kbps, Nq=8, token/s=6002025.12 | 2.6568 | 2.6818 | 0.9241 | — | 0.9338 | — | — | — | — | — | — | |
| Qwen3Token Rate (t/s)=502026.06 | 2.51 | — | — | — | — | 15.8 | — | 9.4 | 0.3 | 8.91 | 0.61 | |
| EncodecBandwidth=3.0kbps, Nq=4, token/s=3002025.12 | 2.0883 | 2.052 | 0.8835 | — | 0.8926 | — | — | — | — | — | — | |
| SpeechTokenizerParams [M]=103.68, Token Rate=50, Codebook Size=1024, Q=3, Bitrate [kbps]=1.52025.12 | 2.0104 | 1.2241 | 0.778 | 0.7445 | — | — | — | — | — | — | — | |
| DACParams [M]=74.71, Token Rate=75, Codebook Size=1024, Q=2, Bitrate [kbps]=1.52025.12 | 1.7443 | 1.5039 | 0.8218 | 0.8636 | — | — | — | — | — | — | — | |
| EncodecParams [M]=14.85, Token Rate=75, Codebook Size=1024, Q=2, Bitrate [kbps]=1.52025.12 | 1.5132 | 1.5753 | 0.8291 | 0.8228 | — | — | — | — | — | — | — | |
| DACUnified=false, DR=440, TPF=1, TPS=1002025.02 | 1.4986 | 1.2454 | 0.7505 | 0.7775 | — | — | — | — | — | — | — | |
| DACBandwidth=1.0kbps, Nq=1, token/s=1002025.12 | 1.4986 | 1.2454 | 0.7505 | — | 0.7775 | — | — | — | — | — | — |