Update app.py

app.py

@@ -17,7 +17,7 @@ def predict(image):
     filepath = 'caption.mp3'
     return caption, filepath
 
-inputs = gr.input.Image(label="Upload any Image")
+inp = gr.inputs.Image(label="Upload any Image")
 outputs = [
     gr.components.Textbox(type="text",label="Captions"),
     gr.components.Audio(type="filepath",label="audio")
@@ -34,7 +34,7 @@ article="""Echo Sense is an innovative image captioning application that utilize
 
 interface = gr.Interface(
     fn=predict,
-    inputs=inputs,
+    inputs=inp,
     outputs=outputs,
     title="",
     description=description,