HKUSTAudio/xcodec2
Audio-to-Audio
•
Updated
•
22k
•
56
Llasa
TTS foundation model compatible with Llama framework (160k hours tokenized speech data released)
-
-
HKUSTAudio/Llasa-3B
Text-to-Speech • Updated • 3.66k • 469 -
HKUSTAudio/Llasa-8B
Text-to-Speech • Updated • 13.3k • 82 -
HKUSTAudio/Llasa-1B
Text-to-Speech • Updated • 4.43k • 93 -
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech • Updated • 2.51k • 26 -
HKUSTAudio/Llasa_opensource_speech_data_160k_hours_tokenized
Updated • 629 • 25 -
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Paper • 2502.04128 • Published • 24 -
HKUSTAudio/Llasa-3B-Preserve-TextChat
Text-to-Speech • Updated • 17 • 2 -
HKUSTAudio/Llasa-1B-Preserve-TextChat
Text-to-Speech • Updated • 22 • 2 -
HKUSTAudio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko
Text-to-Speech • Updated • 123 • 2 -
HKUSTAudio/Llasa-1B-two-speakers-kore-puck
Text-to-Speech • Updated • 251 • 4