jishengpeng/WavTokenizer · AI Repo StatsJIjishengpeng/WavTokenizer
[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling
Giọng nói & âm thanhPython MIT 115tạo 2024-08-29 #acoustic#audio-representation#codec#dac#encodec#gpt4o#music-representation-learning#semantic#soundstream#speech-language-model#speech-representation#text-to-speech