Update README.md
Browse files
README.md
CHANGED
|
@@ -12,31 +12,4 @@ The paragraphs contain the page number, the position in the page, the size, and
|
|
| 12 |
|
| 13 |
We have created the better and more flexible version of this service, you can check here:
|
| 14 |
|
| 15 |
-
https://huggingface.co/HURIDOCS/pdf-document-layout-analysis
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
## Quick Start
|
| 19 |
-
|
| 20 |
-
Download the service that uses the model:
|
| 21 |
-
|
| 22 |
-
git clone https://github.com/huridocs/pdf_paragraphs_extraction.git
|
| 23 |
-
cd pdf_paragraphs_extraction
|
| 24 |
-
|
| 25 |
-
Start the service:
|
| 26 |
-
|
| 27 |
-
./run start
|
| 28 |
-
|
| 29 |
-
Get the paragraphs from a PDF:
|
| 30 |
-
|
| 31 |
-
curl -X GET -F 'file=@/PATH/TO/PDF/pdf_name.pdf' localhost:5051
|
| 32 |
-
|
| 33 |
-
To stop the server:
|
| 34 |
-
|
| 35 |
-
./run stop
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
## Performance
|
| 39 |
-
|
| 40 |
-
Accuracy: 93.9%
|
| 41 |
-
|
| 42 |
-
Speed: 0.15 seconds per page
|
|
|
|
| 12 |
|
| 13 |
We have created the better and more flexible version of this service, you can check here:
|
| 14 |
|
| 15 |
+
https://huggingface.co/HURIDOCS/pdf-document-layout-analysis
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|