Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
JusperLee
/
Dolphin
like
9
Audio-to-Audio
PyTorch
Safetensors
alibabasglab/VoxCeleb2-mix
English
dolphin
audio-visual
speech-separation
cocktail-party
multimodal
lip-reading
audio-processing
custom_code
arxiv:
2509.23610
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
main
Dolphin
/
.gitattributes
Commit History
initial commit
1d57056
verified
JusperLee
commited on
Sep 16, 2025
JusperLee commited on
