6 results found Sort:

SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling
Created 2024-08-29
23 commits to main branch, last one 19 hours ago
FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.
Created 2023-10-07
71 commits to master branch, last one 10 months ago
unofficial implementation of the High Fidelity Neural Audio Compression
Created 2023-04-15
110 commits to main branch, last one 3 months ago
SimVQ: Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
Created 2024-10-17
14 commits to main branch, last one 5 days ago
A Survey of Spoken Dialogue Models (60 pages)
Created 2024-11-11
21 commits to main branch, last one 19 hours ago
Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'
Created 2023-09-07
41 commits to main branch, last one 4 months ago