AgeOfAlgorithms/Llasa-1b-GPTQ-4bit

Model Description

This is a 4bit GPTQ quantization of Llasa-1B by the HKUSTAudio team. I tested using a script written by GitHub user nivibilla, linked below. The tests were successful, but the quality of the generated voice is often unusable. In case you don't believe me, I'll leave this model up here so you can test it yourself.

Model Sources

• Repository: HKUSTAudio/Llasa-1B
• Paper: LLaSA: Scaling Train-Time and Inference-Time Compute for LLaMA-based Speech Synthesis (Coming soon)
• Test Script: https://github.com/slives-lab/local-llasa-tts_voice/blob/main/llasa_vllm_longtext_inference.ipynb