Update app.py

app.py

@@ -23,7 +23,9 @@ def query(image):
     binary_data = buffer.tobytes()
 
     response = requests.post(API_URL, headers=headers, data=binary_data)
-    return response.json()
+    result = {item['label']: item['score'] for item in response.json()}
+
+    return result
 
 def text_extraction(image):
     global text_content
@@ -110,7 +112,7 @@ def inference(image, text, audio, sentiment_option):
     image_sentiment_output = display_sentiment_results(image_sentiment_results, sentiment_option)
     text_sentiment_output = display_sentiment_results(text_sentiment_results, sentiment_option)
 
-    return extracted_image, extracted_facial_data, extracted_text, image_sentiment_output, text_sentiment_output, lang.upper(), result.text, sentiment_output
+    return extracted_image, extracted_facial_data, extracted_text, image_sentiment_output, text_sentiment_output, lang.upper(), result.text, audio_sentiment_output
 
 title = """<h1 align="center">Cross Model Machine Learning (Sentiment Analysis)</h1>"""
 image_path = "thmbnail.png"
@@ -166,19 +168,19 @@ with block:
             gr.HTML(description)
 
     with gr.Blocks():
-        with gr.Row():
-            with gr.Column():
+        with gr.Column():
+            with gr.Row():
                 image = gr.Image()
                 
                 image_output = gr.Image()
                 text_output = gr.Textbox(label="Text Content")
                 text_sentiment = gr.Textbox(label="Text Sentiment")
-                facial_output = gr.JSON(label="Facial Data")
+                facial_output = gr.Label(label='Facial Data', container=True, scale=2)
 
             with gr.Column():
                 gr.Textbox(label="Text Content")
 
-                output_text_sentiment = gr.Textbox("Text Sentiment")
+                output_text_sentiment = gr.Textbox(label="Text Sentiment")
             
             with gr.Column():
                 audio = gr.Audio(label="Input Audio", show_label=False, type="filepath")