Update README.md

README.md

@@ -17,7 +17,21 @@ Distilgpt2
 The model is fine-tuned and evaluated on the COCO 2017 dataset.
 
 
-## How To use this model.
+## How to use this model using Transformer's pipeline
+
+```
+from transformers import  pipeline
+
+image_to_text = pipeline("image-to-text", model="yesidcanoc/image-captioning-swin-tiny-distilgpt2")
+
+# Provide path the image file
+caption = image_to_text("./COCO_val2014_000000457986.jpg")
+print(caption)
+
+```
+
+
+## How To use this model using `GenerateCaptions` utility class.
 
 Adapt the code below to your needs. 
 ```
@@ -106,5 +120,6 @@ print(captions)
 
 ```
 
+
 ## References
 - Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. ArXiv. /abs/2103.14030