TTS foundation model compatible with Llama framework (160k hours tokenized speech data released)
HKUST Audio
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
Collections
2
models
11
HKUSTAudio/Llasa-1B
Text-to-Speech
•
Updated
•
1.89k
•
77
HKUSTAudio/Llasa-8B
Text-to-Speech
•
Updated
•
966
•
47
HKUSTAudio/Llasa-3B
Text-to-Speech
•
Updated
•
7.08k
•
415
HKUSTAudio/xcodec2
Audio-to-Audio
•
Updated
•
15.2k
•
35
HKUSTAudio/YuE-s1-7B-anneal-en-icl
Text-to-Audio
•
Updated
•
24
•
9
HKUSTAudio/YuE-s1-7B-anneal-jp-kr-cot
Text-to-Audio
•
Updated
•
15
HKUSTAudio/YuE-s1-7B-anneal-jp-kr-icl
Text Generation
•
Updated
•
8
HKUSTAudio/YuE-s1-7B-anneal-zh-icl
Text Generation
•
Updated
•
7
HKUSTAudio/YuE-s1-7B-anneal-zh-cot
Text Generation
•
Updated
•
7
HKUSTAudio/YuE-s2-1B-general
Text Generation
•
Updated
•
37
•
1