BetaRare
jishengpeng/WavTokenizer
[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling
- Owner
- jishengpeng (personal account)
- Stars
- Stars: 1,328
- Forks
- Forks: 115
- Language
- Python
- License
- MIT
- Created
- 2024
- Topics
- acousticaudio-representationcodecgpt4omusic-representation-learningsemanticspeech-representationtext-to-speechspeech-language-modeldac
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by jishengpeng
All 5 repos by jishengpeng- jishengpeng/WavChatStars: 317Alpha
- jishengpeng/ControlSpeechStars: 277PythonAlpha
- jishengpeng/LanguagecodecStars: 208PythonPrototype
- jishengpeng/TextrolSpeechStars: 189PythonPrototype
Nearby in Python
All Python repos- alexgolec/tda-apiStars: 1,328PythonBeta
- SakanaAI/text-to-loraStars: 1,328PythonBeta
- gavrielc/Nano-PDFStars: 1,328PythonBeta
- alexa-pi/AlexaPiStars: 1,328PythonBeta
- sebp/scikit-survivalStars: 1,328PythonBeta
- fgmacedo/python-statemachineStars: 1,328PythonBeta