MOSS-Audio-Tokenizer
OpenMOSS
MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, it supports streaming and variable bitrates, delivering SOTA reconstruction and strong performance in generation and understanding—serving as a unified interface for next-generation native audio language models.
Growth over time
1 data points · 2026-04-08 → 2026-04-08How do you feel about this project?
Ask AI about MOSS-Audio-Tokenizer
Question copied to clipboardWhat is the OpenMOSS/MOSS-Audio-Tokenizer GitHub project? Description: "MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, it supports streaming and variable bitrates, delivering SOTA reconstruction and strong performance in generation and understanding—serving as a unified interface for next-generation native audio language models.". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.
Question is copied to clipboard — paste it after the AI opens.
How to clone MOSS-Audio-Tokenizer
Clone via HTTPS
Clone via SSH
Download ZIP
Download master.zipFound an issue?
Report bugs or request features on the MOSS-Audio-Tokenizer issue tracker:
Open GitHub Issues