Update app.py

app.py

@@ -9,11 +9,15 @@ processor = WhisperProcessor.from_pretrained(checkpoint)
 model = WhisperForConditionalGeneration.from_pretrained(checkpoint)
 text_Interface=gr.Interface.load("models/nlpconnect/vit-gpt2-image-captioning")
 
-def greet(name):
-    return "Hello " + name
+def greet():
+    return "Hello "
 
-
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+with gr.Blocks() as demo:
+    gr.Markdown("Start typing below and then click **Run** to see the output.")
+    with gr.Row():
+        inp = gr.Image(type='pil')
+        out = gr.Textbox()
+    gr.Interface(fn=greet, inputs=inp, outputs=out)
 
 demo.launch()
 text_Interface.launch()