Upload app.py

app.py

@@ -1,11 +1,6 @@
 import gradio as gr
-
-
-
-
 from transformers import GPT2LMHeadModel, GPT2Tokenizer, pipeline
-
-# Initialize the GPT2 model and tokenizer
+    # Initialize the GPT2 model and tokenizer
 tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
 model = GPT2LMHeadModel.from_pretrained("gpt2")
 
@@ -13,6 +8,9 @@ model = GPT2LMHeadModel.from_pretrained("gpt2")
 translation_pipeline =  pipeline("automatic-speech-recognition", model="openai/whisper-large-v2")
 
 
+
+
+
 # Geriatric Depression Scale Quiz Questions
 questions = [
 "Are you basically satisfied with your life?",
@@ -29,10 +27,9 @@ questions = [
 "Do you feel worthless the way you are now?",
 "Do you feel full of energy?",
 "Do you feel that your situation is hopeless?",
-"Do you think that most people are better off than you are?"
+"Do you think that most people are better off than you are?"   
 ]
 
-
 def ask_questions(answers):
     """Calculate score based on answers."""
     score = 0
@@ -52,16 +49,6 @@ 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."""
     answers_str = " ".join(answers)
@@ -69,69 +56,43 @@ def modified_summarize(answers):
     summary_ids = model.generate(inputs, max_length=150, num_beams=5, early_stopping=True)
     return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
 
+
 def assistant(*audio_answers):
-    """Calculate score, translate and summarize answers."""
-    # Convert audio answers to text
-    answers = understand_answers(audio_answers)
+    """Convert audio answers to text, evaluate and provide a summary."""
+    text_answers = understand_answers(audio_answers)
+    summarized_text = modified_summarize(text_answers)
+    score = ask_questions(text_answers)
+    return summarized_text, f"Your score is: {score}/{len(questions)}", text_answers  # Return text_answers as well
+
+# Create the Gradio Blocks interface with button click
+
+def update():
+    audio_answers = [audio.value for audio in inp]  # Using inp as it collects all the audio inputs
+    # Handling the three returned values from the assistant function
+    summarized_text, score_string, text_answers = assistant(*audio_answers)
+    out_last_transcription.value = summarized_text  # Displaying the summarized text
+    out_score.value = score_string  # Displaying the score
+
+with gr.Blocks() as demo:
+    gr.Markdown("Start recording your responses below and then click **Run** to see the transcription and your score.")
     
-    # Calculate score and summarize
-    score = ask_questions(answers)
-    summary = modified_summarize(answers)
+    # Clearly initializing Inputs and Outputs lists for the button click
+    inp = []
     
-    # Convert the summary to speech
-    speech = whisper(summary)
+    # Using Column to nest questions
+    with gr.Column(scale=1, min_width=600):
+        for i, question in enumerate(questions):
+            gr.Markdown(f"**Question {i+1}:** {question}")
+            audio_input = gr.Audio(source="microphone")
+            inp.append(audio_input)
     
-    # Convert the first answer from audio to text (already done in answers[0])
-    text = answers[0]
+    # Two output textboxes: one for the last transcribed answer and another for the score
+    out_last_transcription = gr.Textbox(label="Last Transcribed Answer", placeholder="Last transcribed answer will appear here.")
+    out_score = gr.Textbox(label="Score", placeholder="Your score will appear here.")
     
-    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'},
-    {'name': 'input_3', 'label': 'Question 3:Do you feel that your life is empty?', 'type': 'audio', 'source': 'microphone'},
-    {'name': 'input_4', 'label':'Question 4:Do you often get bored?','type': 'audio', 'source': 'microphone'},
-    {'name': 'input_5', 'label':'Question 5:Are you in good spirits most of the time?','type': 'audio', 'source': 'microphone'},
-    {'name': 'input_6', 'label':'Question 6:Are you afraid that something bad is going to happen to you?','type': 'audio', 'source': 'microphone'},
-    {'name': 'input_7', 'label': 'Question 7:Do you feel happy most of the time?','type': 'audio', 'source': 'microphone'},
-    {'name': 'input_8', 'label':'Question 8:Do you often feel helpless?','type': 'audio', 'source': 'microphone'},
-    {'name': 'input_9', 'label':'Question 9: Do you prefer to stay at home, rather than going out and doing things?','type': 'audio', 'source': 'microphone'},
-    {'name': 'input_10', 'label': 'Question 10: Do you feel that you have more problems with memory than most?','type': 'audio', 'source': 'microphone'},
-    {'name': 'input_11', 'label':'Question 11: Do you think it is wonderful to be alive now?','type': 'audio', 'source': 'microphone'},
-    {'name': 'input_12', 'label': 'Question 12:Do you feel worthless the way you are now?','type': 'audio', 'source': 'microphone'},
-    {'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"),
-    ("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()
-
-# Labeled output components
-labeled_outputs = [
-    ("Score", "text"),
-    ("Summary", "text"),
-    ("Summary (Audio)", gr.components.Audio(type="numpy")),
-    ("First Answer (Text)", "text")
-]
-
+    # Button with click event
+    btn = gr.Button("Run")
+    btn.click(fn=update, inputs=inp, outputs=[out_last_transcription, out_score])
 
 
-# Constructing the Gradio Interface with labeled components
-iface_score = gr.Interface(fn=assistant, 
-                           inputs=labeled_inputs, 
-                           outputs=labeled_outputs)
-iface_score.launch()
+demo.launch()