Skip to content
/ xcodec Public

AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

112 stars 5 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

zhenye234/xcodec

BranchesTags

Repository files navigation

X-Codec

Paper Title

Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

ckpts

Speech ckpts downlaod link

General audio ckpts [Soon]

Inference

python inference.py

Training

torchrun --nnodes=1 --nproc-per-node=8 main_launch_vqdp.py

Acknowledgement

I would like to extend a special thanks to authors of Uniaudio and DAC, since our code base is mainly borrowed from Uniaudio and [DAC] (https://github.com/descriptinc/descript-audio-codec).

About

AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

Topics

audio music semantic text-to-speech tokenizer speech sound codec audio-codec gpt language-model self-supervised-learning text-to-music vall-e text-to-sound speech-language-model

Resources

Readme
Activity

Stars

112 stars

Watchers

8 watching

Forks

5 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages