Upload app.py

app.py

@@ -1,4 +1,8 @@
 import gradio as gr
+
+
+
+
 from transformers import GPT2LMHeadModel, GPT2Tokenizer, pipeline
 
 # Initialize the GPT2 model and tokenizer
@@ -8,6 +12,7 @@ model = GPT2LMHeadModel.from_pretrained("gpt2")
 # Initialize the Whisper GPT model
 translation_pipeline =  pipeline("automatic-speech-recognition", model="openai/whisper-large-v2")
 
+
 # Geriatric Depression Scale Quiz Questions
 questions = [
 "Are you basically satisfied with your life?",
@@ -27,6 +32,7 @@ questions = [
 "Do you think that most people are better off than you are?"
 ]
 
+
 def ask_questions(answers):
     """Calculate score based on answers."""
     score = 0
@@ -46,11 +52,15 @@ def understand_answers(audio_answers):
         text_answers.append(transcript[0]['generated_text'])
     return text_answers
 
+# Removing the understand function as it's functionality is covered by understand_answers
+
+# Keeping the whisper function for text-to-speech conversion
 def whisper(text):
     """Convert text to speech using the Whisper TTS model."""
     tts_pipeline = pipeline("text-to-speech", model="facebook/wav2vec2-base-960h")
     speech = tts_pipeline(text)
     return speech[0]['generated_text']
+    
 
 def modified_summarize(answers):
     """Summarize answers using the GPT2 model."""
@@ -76,6 +86,10 @@ def assistant(*audio_answers):
     
     return {"score": f"Score: {score}", "summary": f"Summary: {summary}", "speech": speech, "text": text}
 
+# Labeled input components
+#labeled_inputs = [(f"Question {i+1}: {question}", gr.components.Audio(source="microphone")) for i, question in enumerate(questions)]
+
+
 labeled_inputs = [
     {'name': 'input_1', 'label': 'Question 1: Are you basically satisfied with your life?', 'type': 'audio', 'source': 'microphone'},
     {'name': 'input_2', 'label': 'Question 2: Have you dropped many of your activities and interests?', 'type': 'audio', 'source': 'microphone'},
@@ -92,8 +106,9 @@ labeled_inputs = [
     {'name': 'input_13', 'label': 'Question 13:Do you feel full of energy?','type': 'audio', 'source': 'microphone'},
     {'name': 'input_14', 'label': 'Question 14:Do you feel that your situation is hopeless?','type': 'audio', 'source': 'microphone'},
     {'name': 'input_15', 'label': 'Question 15:Do you think that most people are better off than you are?','type': 'audio', 'source': 'microphone'}
-]
+    ]
 
+# Labeled output components
 labeled_outputs = [
     ("Score", "text"),
     ("Summary", "text"),
@@ -101,5 +116,22 @@ labeled_outputs = [
     ("First Answer (Text)", "text")
 ]
 
+# Constructing the Gradio Interface with labeled components
 iface_score = gr.Interface(fn=assistant, inputs=labeled_inputs, outputs=labeled_outputs)
-iface_score.launch()
+iface_score.launch()
+
+# Labeled output components
+labeled_outputs = [
+    ("Score", "text"),
+    ("Summary", "text"),
+    ("Summary (Audio)", gr.components.Audio(type="numpy")),
+    ("First Answer (Text)", "text")
+]
+
+
+
+# Constructing the Gradio Interface with labeled components
+iface_score = gr.Interface(fn=assistant, 
+                           inputs=labeled_inputs, 
+                           outputs=labeled_outputs)
+iface_score.launch()