#
fsq
Here are 4 public repositories matching this topic...
Ultra-low bitrate speech codec (0.27-1 kbps) with cross-modal alignment and real-time capabilities
semantic speech vae codec cross-modal speaker fsq speech-codec speech-representation contrastive-learning single-codebook
-
Updated
Aug 27, 2025 - Python
[FG 2024] Finite Scalar Quantization as Facial Tokenizer for Dyadic Reaction Generation
-
Updated
Apr 30, 2025 - Python
Improve this page
Add a description, image, and links to the fsq topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the fsq topic, visit your repo's landing page and select "manage topics."