---
title: mini-omni-safetensors
canonical_url: "https://www.modelscope.cn/models/LLM-Research/mini-omni-safetensors"
md_url: "https://www.modelscope.cn/models/LLM-Research/mini-omni-safetensors.md"
repository: LLM-Research/mini-omni-safetensors
last_updated: 2024-09-09
license: mit
base_model:
  - Qwen/Qwen2-0.5B
base_model_relation: finetune
parameters: 694.3M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 2146
stars: 0
---

# mini-omni-safetensors

> mini-omni-safetensors - LLM-Research 在 ModelScope 开源的模型。Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

LLM-Research/mini-omni-safetensors 是 ModelScope 魔搭社区上的 694.3M 参数机器学习模型，采用 mit 许可，基于 Qwen/Qwen2-0.5B 构建。

- **Repository**: LLM-Research/mini-omni-safetensors
- **License**: mit
- **Parameters**: 694.3M
- **Base model**: Qwen/Qwen2-0.5B
- **Downloads**: 2146
- **Stars**: 0
- **Last updated**: 2024-09-09

Source: https://www.modelscope.cn/models/LLM-Research/mini-omni-safetensors

---

<p align="center"><strong style="font-size: 18px;">
Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming
</strong>
</p>

<p align="center">
🤗 <a href="">Hugging Face</a>   | 📖 <a href="https://github.com/gpt-omni/mini-omni">Github</a> 
|     📑 <a href="https://arxiv.org/abs/2408.16725">Technical report</a>
</p>

**This is a safetensors conversion of `gpt-omni/mini-omni`.**

Mini-Omni is an open-source multimodel large language model that can **hear, talk while thinking**. Featuring real-time end-to-end speech input and **streaming audio output** conversational capabilities.

<p align="center">
    <img src="frameworkv3.jpg" width="100%"/>
</p>


## Features

✅ **Real-time speech-to-speech** conversational capabilities. No extra ASR or TTS models required.

✅ **Talking while thinking**, with the ability to generate text and audio at the same time.

✅ **Streaming audio outupt** capabilities.

✅ With "Audio-to-Text" and "Audio-to-Audio" **batch inference** to further boost the performance.

**NOTE**: please refer to https://github.com/gpt-omni/mini-omni for more details.