HKUSTAudio/xcodec2
Audio-to-Audio
•
Updated
•
18.2k
•
57
Llasa
TTS foundation model compatible with Llama framework (160k hours tokenized speech data released)
-
-
HKUSTAudio/Llasa-3B
Text-to-Speech • Updated • 3.39k • 470 -
HKUSTAudio/Llasa-8B
Text-to-Speech • Updated • 13.1k • 82 -
HKUSTAudio/Llasa-1B
Text-to-Speech • Updated • 5.75k • 94 -
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech • Updated • 2.01k • 26 -
HKUSTAudio/Llasa_opensource_speech_data_160k_hours_tokenized
Updated • 577 • 25 -
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Paper • 2502.04128 • Published • 25 -
HKUSTAudio/Llasa-3B-Preserve-TextChat
Text-to-Speech • Updated • 37 • 2 -
HKUSTAudio/Llasa-1B-Preserve-TextChat
Text-to-Speech • Updated • 33 • 2 -
HKUSTAudio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko
Text-to-Speech • Updated • 145 • 2 -
HKUSTAudio/Llasa-1B-two-speakers-kore-puck
Text-to-Speech • Updated • 285 • 4