Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
novateur
/
WavTokenizer
like
46
Text-to-Speech
audio-feature-extraction
speech-language-models
gpt4-o
tokenizer
codec-representation
automatic-speech-recognition
arxiv:
2408.16532
arxiv:
2402.12208
License:
mit
Model card
Files
Files and versions
Community
2
60e8581
WavTokenizer
/
wavtokenizer_smalldata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml
Commit History
Upload 2 files
af1973e
verified
novateur
commited on
Sep 3
