HKUSTAudio
/

Llasa-1B-two-speakers-kore-puck

Model card Files Files and versions

Update (2025-02-13): Add Llasa finetune instruction.

LLaSA: Scaling Train-Time and Inference-Time Compute for LLaMA-based Speech Synthesis

Downloads last month: 30

Safetensors

Model size

2B params

Tensor type

BF16

·

Model tree for HKUSTAudio/Llasa-1B-two-speakers-kore-puck

Base model

meta-llama/Llama-3.2-1B-Instruct

Finetuned

HKUSTAudio/Llasa-1B

Finetuned

(3)

this model

Spaces using HKUSTAudio/Llasa-1B-two-speakers-kore-puck 2

Collection including HKUSTAudio/Llasa-1B-two-speakers-kore-puck

Llasa

TTS foundation model compatible with Llama framework (160k hours tokenized speech data released) • 11 items • Updated May 11, 2025 • 21

Paper for HKUSTAudio/Llasa-1B-two-speakers-kore-puck

Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis

Paper • 2502.04128 • Published Feb 6, 2025 • 27