1 result found Sort:

jishengpeng
WavTokenizer jishengpeng
62
930
mit
22
SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling
dac codec gpt4o encodec acoustic semantic soundstream text-to-speech audio-representation speech-language-model speech-representation music-representation-learning
Created 2024-08-29
30 commits to main branch, last one 25 days ago