upd readme

README.md

@@ -11,15 +11,15 @@ tags:
   - trust-remote-code
 ---
 
-# MossAudioTokenizer
+# Moss-Audio-Tokenizer-V2
 
-This is the code for MOSS-Audio-Tokenizer presented in [MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models](https://arxiv.org/abs/2602.10934). 
+This is the code for the 48khz stereo version of MOSS-Audio-Tokenizer presented in [MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models](https://arxiv.org/abs/2602.10934). 
 
-**MOSSAudioTokenizer** is a unified discrete audio tokenizer based on the **Cat** (**C**ausal **A**udio **T**okenizer with **T**ransformer) architecture. Scaling to 1.6 billion parameters, it functions as a unified discrete interface, delivering both lossless-quality reconstruction and high-level semantic alignment.
+**MOSS-Audio-Tokenizer-V2** is a unified discrete audio tokenizer based on the **Cat** (**C**ausal **A**udio **T**okenizer with **T**ransformer) architecture. Scaling to 2 billion parameters, it functions as a unified discrete interface, delivering both lossless-quality reconstruction and high-level semantic alignment.
 
 **Key Features:**
 
-*   **Extreme Compression & Variable Bitrate**: It compresses 48kHz stereo audio into a remarkably low frame rate of 12.5Hz. Utilizing a 32-layer Residual LFQ quantizer stack, it supports high-fidelity reconstruction across a wide range of bitrates.
+*   **Extreme Compression & Variable Bitrate**: It compresses 48kHz stereo audio into a remarkably low frame rate of 12.5Hz. Utilizing a 32-layer Residual Vector Quantization stack, it supports high-fidelity reconstruction across a wide range of bitrates.
 *   **Pure Transformer Architecture**: The model features a "CNN-free" homogeneous architecture built entirely from Causal Transformer blocks. With 1.6B combined parameters (Encoder + Decoder), it ensures exceptional scalability and supports low-latency streaming inference.
 *   **Large-Scale General Audio Training**: Trained on 3 million hours of diverse audio data, the model excels at encoding and reconstructing all audio domains, including speech, sound effects, and music.
 *   **Unified Semantic-Acoustic Representation**: While achieving state-of-the-art reconstruction quality, Cat produces discrete tokens that are "semantic-rich," making them ideal for downstream tasks like speech understanding (ASR) and generation (TTS).
@@ -42,7 +42,7 @@ import torch
 from transformers import AutoModel
 import torchaudio
 
-repo_id = "OpenMOSS-Team/MOSS-Audio-Tokenizer"
+repo_id = "OpenMOSS-Team/MOSS-Audio-Tokenizer-V2"
 model = AutoModel.from_pretrained(repo_id, trust_remote_code=True).eval()
 
 wav, sr = torchaudio.load('demo/demo_gt.wav')
@@ -92,7 +92,7 @@ The quantizer always runs in fp32.
 import torch
 from transformers import AutoModel
 
-repo_id = "OpenMOSS-Team/MOSS-Audio-Tokenizer"
+repo_id = "OpenMOSS-Team/MOSS-Audio-Tokenizer-V2"
 model = AutoModel.from_pretrained(repo_id, trust_remote_code=True).eval()
 audio = torch.randn(2, 48000 * 6)  # dummy stereo waveform
 
@@ -121,5 +121,18 @@ batch_dec = model.batch_decode(codes_list, chunk_duration=0.08)
 ## Citation
 If you use this code or result in your paper, please cite our work as:
 ```tex
-
+@misc{gong2026mossaudiotokenizerscaling,
+  title={MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models},
+  author={Yitian Gong and Kuangwei Chen and Zhaoye Fei and Xiaogui Yang and Ke Chen and Yang Wang and Kexin Huang and Mingshu Chen and Ruixiao Li and Qingyuan Cheng and Shimin Li and Xipeng Qiu},
+  year={2026},
+  eprint={2602.10934},
+  archivePrefix={arXiv},
+  primaryClass={cs.SD},
+  url={https://arxiv.org/abs/2602.10934}
+}
 ```
+
+## License
+<!-- TODO: check and add license -->
+MOSS-Audio-Tokenizer-V2 is released under the Apache 2.0 license.
+