Update README.md

README.md

@@ -13,9 +13,15 @@ base_model: google/pix2struct-base
 
 *Turn table images into HTML!*
 
+
+## Demo app
+
+Try the [demo app]() which contains both table detection and recognition!
+
+
 ## About
 
-This model takes an image of a table and outputs HTML - the model parses both the optical character recognition (OCR) and the structure to HTML format. 
+This model takes an image of a table and outputs HTML - the model parses the image and performs optical character recognition (OCR) and structure recognition to HTML format. 
 
 The model expects an image containing only a table. If the table is embedded in a document, first use a table detection model to extract it.
 
@@ -25,7 +31,7 @@ The model has been trained using two datasets: [MMTab](https://huggingface.co/da
 
 ## Usage
 
-Below is a complete example for loading the model and performing inference on an example table image:
+Below is a complete example of loading the model and performing inference on an example table image (example from the [MMTab dataset](https://huggingface.co/datasets/SpursgoZmy/MMTab)):
 
 ```python
 import torch
@@ -42,7 +48,6 @@ model.to(device)
 model.eval()
 
 # Load example image from URL
-# Example from the MMTab dataset
 url = "https://example.com/path_to_table_image.jpg"
 response = requests.get(url)
 image = Image.open(BytesIO(response.content))
@@ -59,11 +64,3 @@ predictions_decoded = processor.tokenizer.batch_decode(predictions, skip_special
 # Show predictions as text
 print(predictions_decoded[0])
 ```
-
-
-
-
-
-## Demo app
-
-Try the [demo app]() which contain both table detection and recognition!