Merge branch 'main' of https://huggingface.co/spaces/flax-community/koclip

image2text.py

@@ -15,8 +15,10 @@ def app(model_name):
     st.title("Zero-shot Image Classification")
     st.markdown(
         """
-        Some text goes in here.
-    """
+        This demonstration explores capability of KoCLIP in the field of Zero-Shot Prediction. This demo takes a set of image and captions from, and predicts the most likely label among the different captions given.   
+        
+ KoCLIP is a retraining of OpenAI's CLIP model using 82,783 images from [MSCOCO](https://cocodataset.org/#home) dataset and Korean caption annotations. Korean translation of caption annotations were obtained from [AI Hub](https://aihub.or.kr/keti_data_board/visual_intelligence). Base model `koclip` uses `klue/roberta` as text encoder and `openai/clip-vit-base-patch32` as image encoder. Larger model `koclip-large` uses `klue/roberta` as text encoder and bigger `google/vit-large-patch16-224` as image encoder.    
+ """
     )
 
     query1 = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])