HKUSTAudio/xcodec2
Audio-to-Audio
•
0.8B
•
Updated
•
22.7k
•
91
Llasa
TTS foundation model compatible with Llama framework (160k hours tokenized speech data released)
-
-
HKUSTAudio/Llasa-1B
Text-to-Speech • 1B • Updated • 8.59k • 100 -
HKUSTAudio/Llasa-3B
Text-to-Speech • 4B • Updated • 1.69k • 522 -
HKUSTAudio/Llasa-8B
Text-to-Speech • 9B • Updated • 977 • 96 -
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech • 2B • Updated • 1.58k • 39 -
HKUSTAudio/Llasa_opensource_speech_data_160k_hours_tokenized
Updated • 505 • 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 • 7 • 2 -
HKUSTAudio/Llasa-1B-Preserve-TextChat
Text-to-Speech • 2B • Updated • 5 • 2 -
HKUSTAudio/Llasa-1B-multi-speakers-genshin-zh-en-ja-ko
Text-to-Speech • 2B • Updated • 34 • 5 -
HKUSTAudio/Llasa-1B-two-speakers-kore-puck
Text-to-Speech • 2B • Updated • 15 • 5