HKUSTAudio/Llasa_opensource_speech_data_160k_hours_tokenized
Updated
•
362
•
21
Llasa
TTS foundation model compatible with Llama framework (160k hours tokenized speech data released)
-
-
HKUSTAudio/Llasa-1B-Multilingual
Text-to-Speech • Updated • 498 • 13 -
HKUSTAudio/Llasa-8B
Text-to-Speech • Updated • 1.57k • 55 -
HKUSTAudio/Llasa-3B
Text-to-Speech • Updated • 7.88k • 426 -
HKUSTAudio/Llasa-1B
Text-to-Speech • Updated • 2.31k • 81 -
HKUSTAudio/xcodec2
Audio-to-Audio • Updated • 21.2k • 40 -
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Paper • 2502.04128 • Published • 19