List your company

Speech Reconstruction on LibriSpeech English (test-clean)

0.97SIMMOSS-Audio-Tokenizer
0.33560.50030.6650.8297Feb 11, 2026Feb 16, 2026Feb 22, 2026Feb 28, 2026Mar 6, 2026Mar 12, 2026Mar 18, 2026

Evaluation results

MethodLinks
MOSS-Audio-Tokenizerbps=4000, Frame rate=12.5, NVQ=322026.020.970.973.953.69
MOSS-Audio-Tokenizerbps=4000, Frame rate=12.5, NVQ=322026.030.970.973.953.69
MOSS-Audio-Tokenizerbps=3000, Frame rate=12.5, NVQ=242026.020.960.973.93.61
MOSS-Audio-Tokenizerbps=3000, Frame rate=12.5, NVQ=242026.030.960.973.93.61
Qwen3-TTS-Tokenizerbps=2200, Frame rate=12.5, NVQ=162026.020.950.963.663.19
MOSS-Audio-Tokenizerbps=2000, Frame rate=12.5, NVQ=162026.020.950.963.783.41
Qwen3-TTS-Tokenizerbps=2200, Frame rate=12.5, NVQ=162026.030.950.963.663.19
MOSS-Audio-Tokenizerbps=2000, Frame rate=12.5, NVQ=162026.030.950.963.783.41
Mimibps=4400, Frame rate=12.5, NVQ=322026.020.940.963.83.43
Mimibps=4400, Frame rate=12.5, NVQ=322026.030.940.963.83.43
MOSS-Audio-Tokenizerbps=1500, Frame rate=12.5, NVQ=122026.020.920.953.643.2
MOSS-Audio-Tokenizerbps=1500, Frame rate=12.5, NVQ=122026.030.920.953.643.2
MiMo-Audio-Tokenizerbps=3650, Frame rate=25, NVQ=202026.020.910.953.733.25
MiMo-Audio-Tokenizerbps=3650, Frame rate=25, NVQ=202026.030.910.953.733.25
Higgs-Audio-Tokenizerbps=2000, Frame rate=25, NVQ=82026.020.90.853.593.11
Higgs-Audio-Tokenizerbps=2000, Frame rate=25, NVQ=82026.030.90.853.593.11
MiMo-Audio-Tokenizerbps=2250, Frame rate=25, NVQ=122026.020.890.953.573.05
Mimibps=2475, Frame rate=12.5, NVQ=182026.020.890.943.492.97
DACbps=6000, Frame rate=75, NVQ=82026.020.890.953.753.41
MiMo-Audio-Tokenizerbps=2250, Frame rate=25, NVQ=122026.030.890.953.573.05
Mimibps=2475, Frame rate=12.5, NVQ=182026.030.890.943.492.97
DACbps=6000, Frame rate=75, NVQ=82026.030.890.953.753.41
MOSS-Audio-Tokenizerbps=1000, Frame rate=12.5, NVQ=82026.020.880.943.382.87
MOSS-Audio-Tokenizerbps=1000, Frame rate=12.5, NVQ=82026.030.880.943.382.87
Encodecbps=4500, Frame rate=75, NVQ=62026.020.860.922.912.46
Encodecbps=4500, Frame rate=75, NVQ=62026.030.860.922.912.46
XY-Tokenizerbps=1000, Frame rate=12.5, NVQ=82026.020.850.923.12.5
SpeechTokenizerbps=4000, Frame rate=50, NVQ=82026.020.850.923.052.6
XY-Tokenizerbps=1000, Frame rate=12.5, NVQ=82026.030.850.923.12.5
SpeechTokenizerbps=4000, Frame rate=50, NVQ=82026.030.850.923.052.6
BigCodecbps=1040, Frame rate=80, NVQ=12026.020.840.933.272.68
BigCodecbps=1040, Frame rate=80, NVQ=12026.030.840.933.272.68
XCodec2.0bps=800, Frame rate=50, NVQ=12026.020.820.923.042.43
MOSS-Audio-Tokenizerbps=750, Frame rate=12.5, NVQ=62026.020.820.933.142.6
XCodec2.0bps=800, Frame rate=50, NVQ=12026.030.820.923.042.43
MOSS-Audio-Tokenizerbps=750, Frame rate=12.5, NVQ=62026.030.820.933.142.6
MiMo-Audio-Tokenizerbps=850, Frame rate=25, NVQ=42026.020.80.912.942.39
MiMo-Audio-Tokenizerbps=850, Frame rate=25, NVQ=42026.030.80.912.942.39
Higgs-Audio-Tokenizerbps=1000, Frame rate=25, NVQ=42026.020.770.833.032.48
Higgs-Audio-Tokenizerbps=1000, Frame rate=25, NVQ=42026.030.770.833.032.48
Mimibps=1100, Frame rate=12.5, NVQ=82026.020.740.912.82.25
DACbps=3000, Frame rate=75, NVQ=42026.020.740.92.762.31
Mimibps=1100, Frame rate=12.5, NVQ=82026.030.740.912.82.25
DACbps=3000, Frame rate=75, NVQ=42026.030.740.92.762.31
SpeechTokenizerbps=2000, Frame rate=50, NVQ=42026.020.660.882.381.92
SpeechTokenizerbps=2000, Frame rate=50, NVQ=42026.030.660.882.381.92
StableCodecbps=700, Frame rate=25, NVQ=22026.020.620.912.912.24
StableCodecbps=700, Frame rate=25, NVQ=22026.030.620.912.912.24
Encodecbps=1500, Frame rate=75, NVQ=22026.020.60.851.941.56
Encodecbps=1500, Frame rate=75, NVQ=22026.030.60.851.941.56
DACbps=1500, Frame rate=75, NVQ=22026.020.480.831.871.48
DACbps=1500, Frame rate=75, NVQ=22026.030.480.831.871.48
SpeechTokenizerbps=1000, Frame rate=50, NVQ=22026.020.360.771.591.25
SpeechTokenizerbps=1000, Frame rate=50, NVQ=22026.030.360.771.591.25