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
16
HKUSTAudio/Llasa-1B
Text-to-Speech
•
Updated
•
3.3k
•
90
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech
•
Updated
•
1.72k
•
24
HKUSTAudio/Llasa-3B
Text-to-Speech
•
Updated
•
6.09k
•
458
HKUSTAudio/Llasa-8B
Text-to-Speech
•
Updated
•
13.6k
•
66
HKUSTAudio/xcodec2
Audio-to-Audio
•
Updated
•
25.1k
•
47
HKUSTAudio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko
Text-to-Speech
•
Updated
•
81
•
2
HKUSTAudio/Llasa-1B-two-speakers-kore-puck
Text-to-Speech
•
Updated
•
185
•
4
HKUSTAudio/Llasa-1B-Preserve-TextChat
Text-to-Speech
•
Updated
•
9
•
2
HKUSTAudio/Llasa-3B-Preserve-TextChat
Text-to-Speech
•
Updated
•
10
•
2
HKUSTAudio/YuE-s1-7B-anneal-en-icl
Text-to-Audio
•
Updated
•
197
•
14