Hugging Face's logo

Caraaaaa
/
text_image_captioning

Image-to-Text
Transformers
Safetensors
git
Model card Files
xet
Community
Caraaaaa commited on
Commit
43f378e
·
verified ·
1 Parent(s): 69869a8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -2,4 +2,17 @@
2
  datasets:
3
  - Caraaaaa/non_text_image_captioning
4
  pipeline_tag: image-to-text
5
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  datasets:
3
  - Caraaaaa/non_text_image_captioning
4
  pipeline_tag: image-to-text
5
+ ---
6
+
7
+ This model is finetuned on non-text images extracted from documents (i.e.PDF). It is used to analyze the content of the image and produce a descriptive caption.
8
+ It is part of a project to build a software solution capable of processing offline documents (PDFs, Word, PowerPoint, PPT, etc.) to detect WCAG accessibility issues.
9
+
10
+ Example document with non-text images:
11
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b539ab4dd3e248953a6e69/IlcbNsHuzK5JHHixh_dwN.png)
12
+ Extracted Image:
13
+ ![Alt text](https://datasets-server.huggingface.co/assets/Caraaaaa/non_text_image_captioning/--/ca73cb435a60096ff7194f9616a54fde01f69039/--/default/train/10/image/image.jpg)
14
+ Generated caption:
15
+ "Indication of correct signature"
16
+
17
+ - [Training script](https://colab.research.google.com/drive/1QYvXdi0V1AXqlBMR8MpyydNMnK_Vt4dU?usp=sharing)
18
+ - [Github repo](https://github.com/caraaaaa/doc_accessibility?tab=readme-ov-file)