ictnlp / LLaMA-Omni

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
https://arxiv.org/abs/2409.06666
Apache License 2.0
2.62k stars 177 forks source link

About your gradio issue #37

Open thiswillbeyourgithub opened 1 month ago

thiswillbeyourgithub commented 1 month ago

Hi, I noticed in the readme file that you said you had an issue with the stability of the gradio lib for audio streaming.

It turns out that another repository called Omni-mini contains an alternative way to use gradio that could be of interest to you. Here's the link: https://huggingface.co/spaces/gradio/omni-mini