Llasa
Collection
TTS foundation model compatible with Llama framework (160k hours tokenized speech data released)
•
11 items
•
Updated
•
15
Update (2025-02-13): Add Llasa finetune instruction.
These models are not mentioned in the original paper, they are essentially the same as LLaSA 1B and LLaSA 3B, except they have been fine-tuned with a mixed speech and text SFT dataset, which enables the model to retain text-based conversational abilities.
LLaSA: Scaling Train-Time and Inference-Time Compute for LLaMA-based Speech Synthesis
- Downloads last month
- 17
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for HKUSTAudio/Llasa-3B-Preserve-TextChat
Base model
meta-llama/Llama-3.2-3B-Instruct