Update README.md
Browse files
README.md
CHANGED
@@ -12,44 +12,15 @@ Kosmos-2.5 is a multimodal literate model for machine reading of text-intensive
|
|
12 |
|
13 |
[Kosmos-2.5: A Multimodal Literate Model](https://arxiv.org/abs/2309.11419)
|
14 |
|
15 |
-
## NOTE
|
16 |
Since this is a generative model, there is a risk of **hallucination** during the generation process, and it **CAN NOT** guarantee the accuracy of all OCR/Markdown results in the images.
|
17 |
|
18 |
-
##
|
19 |
### Markdown Task
|
20 |
-
|
21 |
-
```text
|
22 |
-
- **1 \[REG\] BLACK SAKURA** 45,455
|
23 |
-
- **1 COOKIE DOH SAUCES** 0
|
24 |
-
- **1 NATA DE COCO** 0
|
25 |
-
- **Sub Total** 45,455
|
26 |
-
- **PB1 (10%)** 4,545
|
27 |
-
- **Rounding** 0
|
28 |
-
- **Total** **50,000**
|
29 |
-
|
30 |
-
Card Payment 50,000
|
31 |
-
```
|
32 |
|
33 |
### OCR Task
|
34 |
-
|
35 |
-
```text
|
36 |
-
55,595,71,595,71,629,55,629,1
|
37 |
-
82,595,481,595,481,635,82,635,[REG] BLACK SAKURA
|
38 |
-
716,590,841,590,841,629,716,629,45,455
|
39 |
-
55,637,71,637,71,672,55,672,1
|
40 |
-
82,637,486,637,486,675,82,675,COOKIE DOH SAUCES
|
41 |
-
818,632,843,632,843,668,818,668,0
|
42 |
-
51,683,71,683,71,719,51,719,1
|
43 |
-
82,683,371,683,371,719,82,719,NATA DE COCO
|
44 |
-
820,677,845,677,845,713,820,713,0
|
45 |
-
32,770,851,770,851,811,32,811,Sub Total 45,455
|
46 |
-
28,811,853,811,853,858,28,858,PB1 (10%) 4,545
|
47 |
-
28,857,855,857,855,905,28,905,Rounding 0
|
48 |
-
24,905,858,905,858,956,24,956,Total 50,000
|
49 |
-
17,1096,868,1096,868,1150,17,1150,Card Payment 50,000
|
50 |
-
```
|
51 |
-
![output](output.png)
|
52 |
-
|
53 |
|
54 |
## Citation
|
55 |
|
|
|
12 |
|
13 |
[Kosmos-2.5: A Multimodal Literate Model](https://arxiv.org/abs/2309.11419)
|
14 |
|
15 |
+
## NOTE:
|
16 |
Since this is a generative model, there is a risk of **hallucination** during the generation process, and it **CAN NOT** guarantee the accuracy of all OCR/Markdown results in the images.
|
17 |
|
18 |
+
## Inference
|
19 |
### Markdown Task
|
20 |
+
For usage instructions, please refer to [md.py](md.py).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
|
22 |
### OCR Task
|
23 |
+
For usage instructions, please refer to [ocr.py](ocr.py).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
|
25 |
## Citation
|
26 |
|