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
Collections
2
models
19
HKUSTAudio/AudioX
Updated
•
1.74k
•
38
HKUSTAudio/Llasa-1B
Text-to-Speech
•
Updated
•
6.02k
•
96
HKUSTAudio/Llasa-3B
Text-to-Speech
•
Updated
•
2.09k
•
488
HKUSTAudio/Llasa-8B
Text-to-Speech
•
Updated
•
809
•
89
HKUSTAudio/Spark-TTS-0.5B
Text-to-Speech
•
Updated
•
17
•
5
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech
•
Updated
•
899
•
32
HKUSTAudio/VidMuse
Updated
•
4
HKUSTAudio/xcodec2
Audio-to-Audio
•
Updated
•
20.7k
•
66
HKUSTAudio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko
Text-to-Speech
•
Updated
•
23
•
2
HKUSTAudio/Llasa-1B-two-speakers-kore-puck
Text-to-Speech
•
Updated
•
20
•
4