Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens
Paper
•
2602.16687
•
Published
•
2
Potsawee Manakul PRO
potsawee
AI & ML interests
NLP, Summarization, Text Generation and Evaluation, Multimodal
Recent Activity
authored
a paper
1 day ago
Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens
updated
a Space
1 day ago
potsawee/soda-demo
updated
a model
1 day ago
soda-research/soda-135m-base
Organizations
authored
a
paper
1 day ago
updated
a
Space
1 day ago
updated
4
models
1 day ago
liked
a
Space
5 days ago
updated
13
models
7 days ago
soda-research/discrete-audio-isoflop-3e20-4.24B-d2816-L27-B64-b829f0
4B
•
Updated
•
8
soda-research/discrete-audio-isoflop-3e20-1.93B-d2048-L20-B128-ca249f
2B
•
Updated
•
7
soda-research/discrete-audio-isoflop-3e20-2.62B-d2304-L23-B128-29fe40
3B
•
Updated
•
5
soda-research/discrete-audio-isoflop-3e20-1.68B-d1920-L19-B128-a41e32
2B
•
Updated
•
6
soda-research/discrete-audio-isoflop-3e20-851M-d1408-L14-B256-37b469
0.9B
•
Updated
•
6
soda-research/discrete-audio-isoflop-3e20-231M-d640-L7-B256-14d478
0.2B
•
Updated
•
5
soda-research/discrete-audio-isoflop-3e20-375M-d896-L9-B512-781920
0.4B
•
Updated
•
6
soda-research/discrete-audio-isoflop-3e20-1.23B-d1664-L17-B256-5b9328
1B
•
Updated
•
6
soda-research/discrete-audio-isoflop-3e20-588M-d1152-L12-B512-8987cb
0.6B
•
Updated
•
5
soda-research/discrete-audio-isoflop-1.8e20-2.62B-d2304-L23-B64-c4bca8
3B
•
Updated
•
7
soda-research/discrete-audio-isoflop-1.8e20-1.93B-d2048-L20-B64-d639f5
2B
•
Updated
•
5
soda-research/discrete-audio-isoflop-1.8e20-375M-d896-L9-B512-bf11ff
0.4B
•
Updated
•
6
soda-research/discrete-audio-isoflop-1.8e20-588M-d1152-L12-B256-03edb9
0.6B
•
Updated
•
5