Update app.py

app.py

@@ -49,9 +49,9 @@ def zero_shot(image, text_input):
     return {dic["label"]: dic["score"] for dic in res}
 
 def shot(image, labels_text):
-    PIL_image = Image.fromarray(np.uint8(image)).convert('RGB')
+    #PIL_image = Image.fromarray(np.uint8(image)).convert('RGB')
     labels = labels_text.split(",")
-    res = pipe(images=PIL_image, 
+    res = pipe(images= image, 
            candidate_labels=labels,
            hypothesis_template= "This is a photo of a {}")
     return {dic["label"]: dic["score"] for dic in res}
@@ -68,7 +68,7 @@ with gr.Blocks() as demo:
             audio_file =[
             gr.Audio(source="microphone", type="filepath", optional=True),
             gr.Audio(source="upload", type="filepath", optional=True)]
-            text = gr.Textbox(placeholder="If you dont want to record or upload your voice you can input text here")
+            text = gr.Textbox(label="Text", placeholder="If you dont want to record or upload your voice you can input text here")
             with gr.Row():
                 speech_to_text = gr.Button("Speech to text go brrr", css={"margin-top": "1em"})        
         with gr.Column():
@@ -82,7 +82,7 @@ with gr.Blocks() as demo:
             with gr.Row():
                 get_image_latent = gr.Button("Generate Image go brr")         
         with gr.Column():
-            text_input = gr.Textbox(placeholder="input a list of labels separated by commas")
+            text_input = gr.Textbox(label="Candidate labels", placeholder="input a list of labels separated by commas")
             label = gr.Label()
             with gr.Row():
                 zero_shot_clf = gr.Button("Classify Image go brr")