---
language:
  - zh
  - en
license: apache-2.0
tags:
  - omni
  - multimodal
  - text-to-speech
  - audio-to-audio
  - image-to-text
  - minimind
pipeline_tag: text-generation
library_name: transformers
---

<div align="center">

![logo](https://modelscope.cn/studio/gongjy/MiniMind-O/resolve/master/images/logo.png)

</div>

For full documentation, please refer to the GitHub repository: **https://github.com/jingyaogong/minimind-o**

Technical Report: **https://arxiv.org/abs/2605.03937**