EPISODE · Jun 16, 2026 · 1 MIN
OpenMOSS/MOSS-Audio-Tokenizer
from Kana & Mari’s SoundRepos · host Kana & Mari
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.
What this episode covers
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.
NOW PLAYING
OpenMOSS/MOSS-Audio-Tokenizer
No transcript for this episode yet
Similar Episodes
Jul 22, 2025 ·55m
Jul 15, 2025 ·47m
Jul 8, 2025 ·61m
Jun 17, 2025 ·43m