HKUSTAudio/xcodec2
Audio-to-Audio
•
Updated
•
14.9k
•
76
Llasa
TTS foundation model compatible with Llama framework (160k hours tokenized speech data released)
-
-
HKUSTAudio/Llasa-1B
Text-to-Speech • Updated • 8.69k • 99 -
HKUSTAudio/Llasa-3B
Text-to-Speech • Updated • 3.2k • • 507 -
HKUSTAudio/Llasa-8B
Text-to-Speech • Updated • 3.62k • 94 -
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech • Updated • 3.49k • 37 -
HKUSTAudio/Llasa_opensource_speech_data_160k_hours_tokenized
Updated • 1.26k • 29 -
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Paper • 2502.04128 • Published • 26 -
HKUSTAudio/Llasa-3B-Preserve-TextChat
Text-to-Speech • Updated • 19 • 2 -
HKUSTAudio/Llasa-1B-Preserve-TextChat
Text-to-Speech • Updated • 1.77k • 2 -
HKUSTAudio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko
Text-to-Speech • Updated • 1.64k • 4 -
HKUSTAudio/Llasa-1B-two-speakers-kore-puck
Text-to-Speech • Updated • 59 • 4