Update README.md
Browse files
README.md
CHANGED
|
@@ -19,31 +19,43 @@ license_link: LICENSE
|
|
| 19 |
## **Overview**
|
| 20 |
**OmniNeural** is the first fully multimodal model designed specifically for Neural Processing Units (NPUs). It natively understands **text, images, and audio**, and runs across PCs, mobile devices, automobile, IoT, and robotics.
|
| 21 |
|
| 22 |
-
|
| 23 |
-
A fully local, multimodal conversational AI assistant that hears you and sees what you see is finally possible. And it runs on NPU, keeping the battery life long.
|
| 24 |
|
| 25 |
-
|
|
|
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
<table>
|
| 29 |
<tr>
|
| 30 |
-
<td>
|
| 31 |
-
<video
|
| 32 |
-
|
|
|
|
| 33 |
</td>
|
| 34 |
-
|
| 35 |
-
<
|
| 36 |
-
<
|
| 37 |
-
|
| 38 |
-
<p align="center"
|
| 39 |
</td>
|
| 40 |
-
|
| 41 |
-
<
|
| 42 |
-
<
|
|
|
|
|
|
|
| 43 |
</td>
|
| 44 |
</tr>
|
| 45 |
</table>
|
| 46 |
|
|
|
|
|
|
|
| 47 |
---
|
| 48 |
|
| 49 |
## **Key Features**
|
|
|
|
| 19 |
## **Overview**
|
| 20 |
**OmniNeural** is the first fully multimodal model designed specifically for Neural Processing Units (NPUs). It natively understands **text, images, and audio**, and runs across PCs, mobile devices, automobile, IoT, and robotics.
|
| 21 |
|
| 22 |
+
## Demos
|
|
|
|
| 23 |
|
| 24 |
+
### 📱 Demo on Samsung S25 Ultra Mobile Phone NPU
|
| 25 |
+
The first multimodal assistant that sees, hears, and talks with you — running **natively on Snapdragon NPU** for long battery life.
|
| 26 |
|
| 27 |
+
<video controls width="720" preload="metadata"
|
| 28 |
+
src="https://huggingface.co/NexaAI/OmniNeural-4B/resolve/main/assets/MOBILE_50MB.mp4"
|
| 29 |
+
type="video/mp4"></video>
|
| 30 |
+
|
| 31 |
+
---
|
| 32 |
+
|
| 33 |
+
## ✨ Capabilities Highlights on PC NPU
|
| 34 |
|
| 35 |
<table>
|
| 36 |
<tr>
|
| 37 |
+
<td width="33%">
|
| 38 |
+
<video controls width="100%" preload="metadata"
|
| 39 |
+
src="https://huggingface.co/NexaAI/OmniNeural-4B/resolve/main/assets/PC_demo_2_image.mov"></video>
|
| 40 |
+
<p align="center"><b>🖼️ Multi-Image Reasoning</b><br>Spot the difference across two images in multi-round dialogue.</p>
|
| 41 |
</td>
|
| 42 |
+
|
| 43 |
+
<td width="33%">
|
| 44 |
+
<video controls width="100%" preload="metadata"
|
| 45 |
+
src="https://huggingface.co/NexaAI/OmniNeural-4B/resolve/main/assets/PC_Demo_Audio.mov"></video>
|
| 46 |
+
<p align="center"><b>🎤 Image + Audio → Function Call</b><br>Snap a poster, add a voice note, model fires a function call.</p>
|
| 47 |
</td>
|
| 48 |
+
|
| 49 |
+
<td width="33%">
|
| 50 |
+
<video controls width="100%" preload="metadata"
|
| 51 |
+
src="https://huggingface.co/NexaAI/OmniNeural-4B/resolve/main/assets/PC_Demo_Agent.mov"></video>
|
| 52 |
+
<p align="center"><b>🎶 Multi-Audio Comparison</b><br>Tell apart two music clips locally.</p>
|
| 53 |
</td>
|
| 54 |
</tr>
|
| 55 |
</table>
|
| 56 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
---
|
| 60 |
|
| 61 |
## **Key Features**
|