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
Text-to-Audio
•
Updated
•
2.19k
•
50
HKUSTAudio/Llasa-1B
Text-to-Speech
•
Updated
•
6.84k
•
97
HKUSTAudio/Llasa-3B
Text-to-Speech
•
Updated
•
3.26k
•
493
HKUSTAudio/Llasa-8B
Text-to-Speech
•
Updated
•
1.17k
•
92
HKUSTAudio/Spark-TTS-0.5B
Text-to-Speech
•
Updated
•
9
•
5
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech
•
Updated
•
1.02k
•
35
HKUSTAudio/VidMuse
Updated
•
4
HKUSTAudio/xcodec2
Audio-to-Audio
•
Updated
•
33.2k
•
67
HKUSTAudio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko
Text-to-Speech
•
Updated
•
50
•
3
HKUSTAudio/Llasa-1B-two-speakers-kore-puck
Text-to-Speech
•
Updated
•
20
•
4