Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
declare-lab
/
JAM-0.5
like
25
Follow
Deep Cognition and Language Research (DeCLaRe) Lab
156
Text-to-Audio
Diffusers
English
music
art
song-generation
lyrics-to-song
flow-matching
direct-preference-optimization
arxiv:
2507.20880
License:
other
Model card
Files
Files and versions
xet
Community
1
Use this model
main
JAM-0.5
2.2 GB
5 contributors
History:
13 commits
This model has 1 file scanned as unsafe.
Show
files
liu-hanghang
Update README.md
1f1e53f
verified
5 months ago
.gitattributes
1.52 kB
initial commit
5 months ago
LICENSE.md
2.88 kB
Upload folder using huggingface_hub
5 months ago
README.md
13 kB
Update README.md
5 months ago
en_us_cmudict_ipa_forward.pt
65.6 MB
xet
Revert "Added files"
5 months ago
jam-0_5.safetensors
2.13 GB
xet
Upload folder using huggingface_hub
5 months ago
jam_infer.yaml
1.46 kB
Create jam_infer.yaml
5 months ago
silience_latent.pt
112 kB
xet
Revert "Added files"
5 months ago
vocal.npy
2.18 kB
xet
Revert "Added files"
5 months ago