Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,16 @@ base_model:
|
|
| 22 |
```bash
|
| 23 |
nexa infer NexaAI/DeepSeek-OCR-GGUF
|
| 24 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Model Description
|
| 27 |
**DeepSeek OCR** is a high-accuracy optical character recognition model built for extracting text from complex visual inputs such as documents, screenshots, receipts, and natural scenes.
|
|
|
|
| 22 |
```bash
|
| 23 |
nexa infer NexaAI/DeepSeek-OCR-GGUF
|
| 24 |
```
|
| 25 |
+
3. Then drag your image to terminal or type into the image path
|
| 26 |
+
1. extract text
|
| 27 |
+
```bash
|
| 28 |
+
<your-image-path> Free OCR.
|
| 29 |
+
```
|
| 30 |
+
2. extract bounding box
|
| 31 |
+
```bash
|
| 32 |
+
<your-image-path> <|grounding|>Convert the document to markdown.
|
| 33 |
+
```
|
| 34 |
+
> Note: If the model fails to run, install the latest [Vulkan driver for Windows](https://www.amd.com/en/support/download/drivers.html)
|
| 35 |
|
| 36 |
## Model Description
|
| 37 |
**DeepSeek OCR** is a high-accuracy optical character recognition model built for extracting text from complex visual inputs such as documents, screenshots, receipts, and natural scenes.
|