Update app.py

app.py

@@ -65,41 +65,11 @@ def transcribe(audio, state=""):
 
 # Create a combined function that calls both models
 def get_predictions(audio_input):
-    # Perform transcription to get the text
-    transcribed_text = transcribe(audio_input)
-
-    # Define the API key for DeepAI Text to Image API
-    api_key = 'dee3e3f2-d5cf-474c-8072-bd6bea47e865'
-
-    # Generate the image with the transcribed text using DeepAI Text to Image API
-    image = generate_image(api_key, transcribed_text)
-
-    # Get emotion prediction from audio
     emotion_prediction = predict_emotion_from_audio(audio_input)
+    transcribe_prediction = transcribe(audio_input)
+    return [emotion_prediction, transcribe_prediction]
 
-    return [emotion_prediction, transcribed_text, image]
-
-# Define a function to generate an image using DeepAI Text to Image API
-def generate_image(api_key, text):
-    url = "https://api.deepai.org/api/text2img"
-    headers = {'api-key': api_key}
-    response = requests.post(
-        url,
-        data={
-            'text': text,
-        },
-        headers=headers
-    )
-    response_data = response.json()
-    if 'output_url' in response_data:
-        image_url = response_data['output_url']
-        image_response = requests.get(image_url)
-        image = Image.open(BytesIO(image_response.content))
-        return image
-    else:
-        return None
-
-# Create the Gradio interface for acoustic and semantic predictions
+# Create the Gradio interface
 with gr.Blocks() as interface:
     gr.Markdown("Emotional Machines test: Load or Record an audio file to speech emotion analysis")
     with gr.Tabs():
@@ -107,13 +77,9 @@ with gr.Blocks() as interface:
             with gr.Row():
                 input_audio = gr.Audio(label="Input Audio", type="filepath")
                 submit_button = gr.Button("Submit")
-            output_labels = [gr.Label(num_top_classes=8), gr.Label(num_top_classes=4), gr.Image(type='pil')]
+            output_labels = [gr.Label(num_top_classes=8), gr.Label(num_top_classes=4)]
 
-    # Set the function to be called when the button is clicked for acoustic and semantic predictions
+    # Set the function to be called when the button is clicked
     submit_button.click(get_predictions, inputs=input_audio, outputs=output_labels)
 
-    # Display transcribed text as a label
-    transcribed_text_label = gr.Label(label="Transcribed Text")
-
-# Launch the Gradio interface
 interface.launch()