Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
earlab
/
EAR_VAE2
Like
11
Audio-to-Audio
English
Chinese
music
vae
codec
arxiv:
2608.19843
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
3
Copy to bucket
refs/pr/1
EAR_VAE2
Commit History
Aug 21
09:42
Add pipeline tag
nielsr
HF Staff
Verified signature
f290de0
This PR adds the missing `pipeline_tag: audio-to-audio` to the model card metadata, ensuring the model appears in the audio-to-audio category on the Hub and is easily discoverable for users working on audio reconstruction and music generation tasks.
07:56
Update config.json
earlab
Verified signature
2bce71e
07:56
Create config.json
earlab
Verified signature
c1c84ed
07:55
Update README.md
earlab
Verified signature
62d2872
07:55
Delete configs/ear_vae2.json
earlab
Verified signature
ca2fe59
04:45
update the paper link and other info
earlab
Verified signature
ec2be84
Aug 18
09:21
Upload pics
earlab
Verified signature
344797e
09:19
Update README.md
earlab
Verified signature
efab627
09:16
init weights
earlab
Verified signature
7d9ac58
08:49
initial commit
earlab
Verified signature
ec63b01
