Update app.py

app.py

@@ -4,11 +4,6 @@ import gradio as gr
 import shortuuid
 from transformers import pipeline
 
-#input voice/text 
-#convert text to image via dalle
-#given list of labels and a selected image from gallery do zero-shot classification 
-#tts your output label as: Your output looks like "label of zero-shot"
-
 asr = pipeline("automatic-speech-recognition")
 latent = gr.Interface.load("spaces/multimodalart/latentdiffusion")
 zero = pipeline("zero-shot-image-classification")
@@ -47,7 +42,13 @@ def zero_shot(image, text_input):
     results = zero(image, text_input)
     return {dic["label"]: dic["score"] for dic in results}
     
-with gr.Blocks() as demo:    
+with gr.Blocks() as demo: 
+    gr.Markdown( """
+    #input voice/text 
+    #convert text to image via dalle
+    #given list of labels and a selected image from gallery do zero-shot classification 
+    #Coming soon: tts your output label as: Your output looks like "label of zero-shot"
+     """)    
     with gr.Row():
         with gr.Column():
             audio_file =[