HKUST Audio

non-profit

http://wei-xue.com

wxue_audio

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Xinsheng-Wang submitted a paper about 1 hour ago

SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

lmxue updated a dataset 4 months ago

HKUSTAudio/Audio-FLAN-Dataset

Zeyue7 updated a dataset 8 months ago

HKUSTAudio/VidMuse-V2M-Dataset

View all activity

Collections 2

models 19

HKUSTAudio/Llasa-3B

Text-to-Speech • 4B • Updated May 10, 2025 • 501 • 525

HKUSTAudio/Llasa-1B

Text-to-Speech • 1B • Updated May 10, 2025 • 13.8k • 102

HKUSTAudio/VidMuse

Updated May 8, 2025 • 27 • 5

HKUSTAudio/AudioX

Text-to-Audio • Updated Apr 24, 2025 • 105

HKUSTAudio/Llasa-8B

Text-to-Speech • 9B • Updated Mar 9, 2025 • 714 • 96

HKUSTAudio/Spark-TTS-0.5B

Text-to-Speech • Updated Mar 7, 2025 • 1 • 6

HKUSTAudio/Llasa-1B-Multilingual

Text-to-Speech • 2B • Updated Mar 5, 2025 • 2.89k • 42

HKUSTAudio/xcodec2

Audio-to-Audio • 0.8B • Updated Feb 23, 2025 • 16.8k • 96

HKUSTAudio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko

Text-to-Speech • 2B • Updated Feb 13, 2025 • 24 • 5

HKUSTAudio/Llasa-1B-two-speakers-kore-puck

Text-to-Speech • 2B • Updated Feb 13, 2025 • 10 • 5

datasets 3

HKUSTAudio/Audio-FLAN-Dataset

Preview • Updated Oct 6, 2025 • 285 • 40

HKUSTAudio/VidMuse-V2M-Dataset

Viewer • Updated Jun 10, 2025 • 300 • 87 • 3

HKUSTAudio/Llasa_opensource_speech_data_160k_hours_tokenized

Updated Feb 13, 2025 • 118 • 30