Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
wsntxxn
/
UniFlow-Audio
like
5
Running
on
Zero
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
UniFlow-Audio
/
models
262 kB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
wsntxxn
Unify duration scale: use latent token count for both training and inference
51bd0e0
6 months ago
autoencoder
Init commit
7 months ago
content_encoder
Init commit
7 months ago
dit
Init commit
7 months ago
common.py
Safe
5.67 kB
Init commit
7 months ago
content_adapter.py
Safe
15.6 kB
Init commit
7 months ago
diffusion.py
Safe
35.1 kB
Init commit
7 months ago
flow_matching.py
Safe
40.3 kB
Unify duration scale: use latent token count for both training and inference
6 months ago
