HKUSTAudio/xcodec2
Audio-to-Audio
•
0.8B
•
Updated
•
18.9k
•
94
Llasa
TTS foundation model compatible with Llama framework (160k hours tokenized speech data released)
-
-
HKUSTAudio/Llasa-1B
Text-to-Speech • 1B • Updated • 19.4k • 101 -
HKUSTAudio/Llasa-3B
Text-to-Speech • 4B • Updated • 780 • 523 -
HKUSTAudio/Llasa-8B
Text-to-Speech • 9B • Updated • 751 • 96 -
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech • 2B • Updated • 2.91k • 41 -
HKUSTAudio/Llasa_opensource_speech_data_160k_hours_tokenized
Updated • 274 • 30 -
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Paper • 2502.04128 • Published • 27 -
HKUSTAudio/Llasa-3B-Preserve-TextChat
Text-to-Speech • 4B • Updated • 12 • 2 -
HKUSTAudio/Llasa-1B-Preserve-TextChat
Text-to-Speech • 2B • Updated • 8 • 2 -
HKUSTAudio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko
Text-to-Speech • 2B • Updated • 20 • 5 -
HKUSTAudio/Llasa-1B-two-speakers-kore-puck
Text-to-Speech • 2B • Updated • 9 • 5