search

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
2.61k stars 175 forks source link

Add Replicate demo and API #22

Closed chenxwh closed 2 months ago

chenxwh commented 2 months ago

Hi @Poeroz,

Great work on LLaMA-Omni!

This pull request makes it possible to run StoryDiffusion on Replicate (https://replicate.com/chenxwh/llama-omni) and via API (https://replicate.com/chenxwh/llama-omni/api). Also we'd like to transfer the demo page to ICTNLP so you can make modifications easily, and happy to help maintain/integrate the upcoming changes and improving the demo :)

Poeroz commented 2 months ago

Hi Chenxi,

Thank you for helping us deploy the model on Replicate. Could you please let us know how to transfer the demo pages to ICTNLP? Thank you!

chenxwh commented 2 months ago

Hi Chenxi,

Thank you for helping us deploy the model on Replicate. Could you please let us know how to transfer the demo pages to ICTNLP? Thank you!

It is now under https://replicate.com/ictnlp/llama-omni :)