HKUSTAudio/xcodec2
Audio-to-Audio
•
Updated
•
41.7k
•
69
Llasa
TTS foundation model compatible with Llama framework (160k hours tokenized speech data released)
-
-
HKUSTAudio/Llasa-1B
Text-to-Speech • Updated • 9.87k • 98 -
HKUSTAudio/Llasa-3B
Text-to-Speech • Updated • 2.86k • 497 -
HKUSTAudio/Llasa-8B
Text-to-Speech • Updated • 1.28k • 94 -
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech • Updated • 1.02k • 35 -
HKUSTAudio/Llasa_opensource_speech_data_160k_hours_tokenized
Updated • 458 • 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 • 2 • 2 -
HKUSTAudio/Llasa-1B-Preserve-TextChat
Text-to-Speech • Updated • 2 • 2 -
HKUSTAudio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko
Text-to-Speech • Updated • 254 • 4 -
HKUSTAudio/Llasa-1B-two-speakers-kore-puck
Text-to-Speech • Updated • 18 • 4