Upload MOSS Audio Tokenizer v2

.gitattributes

@@ -46,4 +46,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text
 *.wav filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text__pycache__/modeling_moss_audio_tokenizer.cpython-312.pyc filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -132,6 +132,59 @@ batch_dec = model.batch_decode(codes_list, chunk_duration=0.08)
   `model-00003-of-00003.safetensors`
 - `demo/demo_gt.wav`
 
+## Evaluation Metrics
+
+The table below compares the reconstruction quality of open-source audio tokenizers with MOSS-Audio-Tokenizer-v2 on speech and audio/music data.
+
+- Speech metrics are evaluated on LibriSpeech test-clean (English) and AISHELL-2 (Chinese), reported as EN/ZH.
+- Audio metrics are evaluated on the AudioSet evaluation subset, while music metrics are evaluated on MUSDB, reported as audio/music.
+- STFT-Dist. denotes the STFT distance.
+- Higher is better for speech metrics, while lower is better for audio/music metrics (Mel-Loss, STFT-Dist.).
+- Nq denotes the number of quantizers.
+
+| Model | bps | Frame rate | Nq | Speech: SIM ↑ (EN/ZH) | Speech: STOI ↑ (EN/ZH) | Speech: PESQ-NB ↑ (EN/ZH) | Speech: PESQ-WB ↑ (EN/ZH) | Audio/Music: Mel-Loss ↓ | Audio/Music: STFT-Dist. ↓ |
+| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| **XCodec2.0** | 800 | 50 | 1 | 0.82 / 0.74 | 0.92 / 0.86 | 3.04 / 2.46 | 2.43 / 1.96 | -- / -- | -- / -- |
+| **MiMo Audio Tokenizer** | 850 | 25 | 4 | 0.80 / 0.74 | 0.91 / 0.87 | 2.94 / 2.62 | 2.39 / 2.14 | **0.82** / 0.81 | 2.33 / 2.23 |
+| **Higgs Audio Tokenizer** | 1000 | 25 | 4 | 0.77 / 0.68 | 0.83 / 0.82 | 3.03 / 2.61 | 2.48 / 2.14 | 0.83 / **0.80** | **2.20** / **2.05** |
+| **SpeechTokenizer** | 1000 | 50 | 2 | 0.36 / 0.25 | 0.77 / 0.68 | 1.59 / 1.38 | 1.25 / 1.17 | -- / -- | -- / -- |
+| **XY-Tokenizer** | 1000 | 12.5 | 8 | 0.85 / 0.79 | 0.92 / 0.87 | 3.10 / 2.63 | 2.50 / 2.12 | -- / -- | -- / -- |
+| **BigCodec** | 1040 | 80 | 1 | 0.84 / 0.69 | 0.93 / 0.88 | 3.27 / 2.55 | 2.68 / 2.06 | -- / -- | -- / -- |
+| **Mimi** | 1100 | 12.5 | 8 | 0.74 / 0.59 | 0.91 / 0.85 | 2.80 / 2.24 | 2.25 / 1.78 | 1.24 / 1.19 | 2.62 / 2.49 |
+| **MOSS-Audio-Tokenizer-v2 (Ours)** | 750 | 12.5 | 6 | 0.82 / 0.75 | 0.92 / 0.88 | 3.14 / 2.68 | 2.59 / 2.19 | 0.93 / 0.91 | 2.28 / 2.14 |
+| **MOSS-Audio-Tokenizer-v2 (Ours)** | 1000 | 12.5 | 8 | **0.88** / **0.80** | **0.94** / **0.90** | **3.39** / **2.93** | **2.88** / **2.43** | 0.88 / 0.86 | 2.22 / 2.07 |
+| **—** | **—** | **—** | **—** | **—** | **—** | **—** | **—** | **—** | **—** |
+| **DAC** | 1500 | 75 | 2 | 0.48 / 0.41 | 0.83 / 0.79 | 1.87 / 1.67 | 1.48 / 1.37 | -- / -- | -- / -- |
+| **Encodec** | 1500 | 75 | 2 | 0.60 / 0.45 | 0.85 / 0.81 | 1.94 / 1.80 | 1.56 / 1.48 | 1.12 / 1.04 | 2.60 / 2.42 |
+| **Higgs Audio Tokenizer** | 2000 | 25 | 8 | 0.90 / 0.83 | 0.85 / 0.85 | 3.59 / 3.22 | 3.11 / 2.73 | 0.74 / 0.70 | **2.07** / **1.92** |
+| **SpeechTokenizer** | 2000 | 50 | 4 | 0.66 / 0.50 | 0.88 / 0.80 | 2.38 / 1.79 | 1.92 / 1.49 | -- / -- | -- / -- |
+| **Qwen3 TTS Tokenizer** | 2200 | 12.5 | 16 | **0.95** / 0.88 | **0.96** / 0.93 | 3.66 / 3.10 | 3.19 / 2.62 | -- / -- | -- / -- |
+| **MiMo Audio Tokenizer** | 2250 | 25 | 12 | 0.89 / 0.83 | 0.95 / 0.92 | 3.57 / 3.25 | 3.05 / 2.71 | **0.70** / **0.68** | 2.21 / 2.10 |
+| **Mimi** | 2475 | 12.5 | 18 | 0.89 / 0.76 | 0.94 / 0.91 | 3.49 / 2.90 | 2.97 / 2.35 | 1.10 / 1.06 | 2.45 / 2.32 |
+| **MOSS-Audio-Tokenizer-v2 (Ours)** | 1500 | 12.5 | 12 | 0.93 / 0.86 | 0.95 / 0.92 | 3.66 / 3.24 | 3.23 / 2.77 | 0.83 / 0.79 | 2.15 / 1.98 |
+| **MOSS-Audio-Tokenizer-v2 (Ours)** | 2000 | 12.5 | 16 | **0.95** / **0.89** | **0.96** / **0.94** | **3.80** / **3.44** | **3.45** / **3.01** | 0.79 / 0.75 | 2.10 / 1.93 |
+| **—** | **—** | **—** | **—** | **—** | **—** | **—** | **—** | **—** | **—** |
+| **DAC** | 3000 | 75 | 4 | 0.74 / 0.67 | 0.90 / 0.88 | 2.76 / 2.47 | 2.31 / 2.07 | 0.86 / 0.83 | 2.23 / 2.10 |
+| **MiMo Audio Tokenizer** | 3650 | 25 | 20 | 0.91 / 0.85 | 0.95 / 0.93 | 3.73 / 3.44 | 3.25 / 2.89 | 0.66 / 0.65 | 2.17 / 2.06 |
+| **SpeechTokenizer** | 4000 | 50 | 8 | 0.85 / 0.69 | 0.92 / 0.85 | 3.05 / 2.20 | 2.60 / 1.87 | -- / -- | -- / -- |
+| **Mimi** | 4400 | 12.5 | 32 | 0.94 / 0.83 | 0.96 / 0.94 | 3.80 / 3.31 | 3.43 / 2.78 | 1.02 / 0.98 | 2.34 / 2.21 |
+| **Encodec** | 4500 | 75 | 6 | 0.86 / 0.75 | 0.92 / 0.91 | 2.91 / 2.63 | 2.46 / 2.15 | 0.91 / 0.84 | 2.33 / 2.17 |
+| **DAC** | 6000 | 75 | 8 | 0.89 / 0.84 | 0.95 / 0.94 | 3.75 / 3.57 | 3.41 / 3.20 | **0.65** / **0.63** | **1.97** / 1.87 |
+| **MOSS-Audio-Tokenizer-v2 (Ours)** | 3000 | 12.5 | 24 | 0.96 / 0.92 | **0.97** / 0.95 | 3.94 / 3.64 | 3.66 / 3.28 | 0.75 / 0.71 | 2.04 / 1.87 |
+| **MOSS-Audio-Tokenizer-v2 (Ours)** | 4000 | 12.5 | 32 | **0.97** / **0.93** | **0.97** / **0.96** | **3.98** / **3.72** | **3.75** / **3.39** | 0.73 / 0.69 | 2.02 / **1.84** |
+
+### LibriSpeech Speech Metrics (MOSS-Audio-Tokenizer-v2 vs. Open-source Tokenizers)
+
+The plots below compare our MOSS-Audio-Tokenizer-v2 model with other open-source speech tokenizers on the LibriSpeech dataset, evaluated with SIM, STOI, PESQ-NB, and PESQ-WB (higher is better).
+We control the bps of the same model by adjusting the number of RVQ codebooks used during inference.
+
+<table>
+  <tr>
+    <td align="center"><br><img src="images/metric.png" width="100%"></td>
+  </tr>
+</table>
+
+
 ## Citation
 If you use this code or result in your paper, please cite our work as:
 ```tex