Update app.py

app.py

@@ -23,7 +23,7 @@ def transcribe(audio_path):
 
     groq_api_endpoint = "https://api.groq.com/openai/v1/audio/transcriptions"
     headers = {
-        "Authorization": "Bearer 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",  # Replace with your actual API key
+        "Authorization": "Bearer YOUR_API_KEY",  # Replace with your actual API key
     }
     files = {
         'file': ('audio.wav', audio_data, 'audio/wav'),
@@ -39,24 +39,24 @@ def transcribe(audio_path):
     if response.status_code == 200:
         result = response.json()
         transcript = result.get("text", "No transcription available.")
-        return generate_notes(transcript)
+        return generate_exam_paper(transcript)
     else:
         error_msg = response.json().get("error", {}).get("message", "Unknown error.")
         print(f"API Error: {error_msg}")
         return create_error_pdf(f"API Error: {error_msg}")
 
-def generate_notes(transcript):
+def generate_exam_paper(transcript):
     try:
         sentences = sent_tokenize(transcript)
     except LookupError:
         sentences = custom_sent_tokenize(transcript)
 
-    # Extract key sentences for generating questions
+    # Extract important sentences for generating questions
     important_sentences = get_important_sentences(sentences)
     
-    # Generate long questions, short questions, and MCQs
-    long_questions = [f"What is meant by '{sentence}'?" for sentence in important_sentences[:5]]
-    short_questions = [f"Define '{sentence.split()[0]}'." for sentence in important_sentences[:5]]
+    # Generate exam-like questions
+    long_questions = [f"Explain the historical significance of '{sentence}'?" for sentence in important_sentences[:5]]
+    short_questions = [f"What is the definition of '{sentence.split()[0]}'?" for sentence in important_sentences[:5]]
 
     mcqs = generate_mcqs(important_sentences)
 
@@ -64,10 +64,10 @@ def generate_notes(transcript):
     return pdf_path
 
 def get_important_sentences(sentences):
-    # Prioritize sentences that contain nouns or verbs to be more relevant
+    # Focus on sentences that are likely to contain key information (like facts or definitions)
     important_sentences = []
     for sentence in sentences:
-        # Simple rule: sentences with nouns/verbs are considered important
+        # Simplified heuristic: sentences with important nouns/verbs
         if len(re.findall(r'\b(NN|VB)\b', sentence)):  # Using POS tags to detect nouns/verbs
             important_sentences.append(sentence)
     return important_sentences[:5]  # Limit to top 5 important sentences
@@ -75,11 +75,11 @@ def get_important_sentences(sentences):
 def generate_mcqs(important_sentences):
     mcqs = []
     for sentence in important_sentences:
-        # Generate MCQs from meaningful sentences
-        key_terms = sentence.split()  # Split sentence into words (simple tokenization)
-        correct_answer = random.choice(key_terms)  # Randomly select a key term from the sentence
-        options = [correct_answer] + random.sample(key_terms, 3)  # Create multiple choice options
-        random.shuffle(options)  # Shuffle options
+        # Generate MCQs from the sentence context
+        key_terms = sentence.split()  # Simple tokenization
+        correct_answer = random.choice(key_terms)  # Select a key term as the answer
+        options = [correct_answer] + random.sample(key_terms, 3)  # Select distractors from the sentence
+        random.shuffle(options)  # Shuffle the options
         mcq = {
             "question": f"What is '{correct_answer}' in the context of the sentence?",
             "options": options,
@@ -91,41 +91,42 @@ def generate_mcqs(important_sentences):
 def create_pdf(transcript, long_questions, short_questions, mcqs):
     pdf = FPDF()
     pdf.add_page()
-    
+
     pdf.set_font("Arial", "B", 16)
-    pdf.cell(200, 10, "Transcription Notes", ln=True, align="C")
+    pdf.cell(200, 10, "Exam Paper: Transcription Notes", ln=True, align="C")
 
     pdf.set_font("Arial", "", 12)
     pdf.multi_cell(0, 10, f"Transcription:\n{transcript.encode('latin1', 'replace').decode('latin1')}\n\n")
 
-    # Add long questions section
+    # Add Long Questions Section
     pdf.set_font("Arial", "B", 14)
     pdf.cell(200, 10, "Long Questions", ln=True)
     pdf.set_font("Arial", "", 12)
-    for question in long_questions:
-        pdf.multi_cell(0, 10, f"- {question.encode('latin1', 'replace').decode('latin1')}\n")
+    for i, question in enumerate(long_questions, 1):
+        pdf.multi_cell(0, 10, f"{i}. {question.encode('latin1', 'replace').decode('latin1')}\n")
 
-    # Add short questions section
+    # Add Short Questions Section
     pdf.set_font("Arial", "B", 14)
     pdf.cell(200, 10, "Short Questions", ln=True)
     pdf.set_font("Arial", "", 12)
-    for question in short_questions:
-        pdf.multi_cell(0, 10, f"- {question.encode('latin1', 'replace').decode('latin1')}\n")
+    for i, question in enumerate(short_questions, 1):
+        pdf.multi_cell(0, 10, f"{i}. {question.encode('latin1', 'replace').decode('latin1')}\n")
 
-    # Add MCQs section
+    # Add MCQs Section
     pdf.set_font("Arial", "B", 14)
     pdf.cell(200, 10, "Multiple Choice Questions (MCQs)", ln=True)
     pdf.set_font("Arial", "", 12)
-    for mcq in mcqs:
-        pdf.multi_cell(0, 10, f"Q: {mcq['question'].encode('latin1', 'replace').decode('latin1')}")
+    for i, mcq in enumerate(mcqs, 1):
+        pdf.multi_cell(0, 10, f"{i}. {mcq['question'].encode('latin1', 'replace').decode('latin1')}")
         for option in mcq["options"]:
             pdf.multi_cell(0, 10, f"   - {option.encode('latin1', 'replace').decode('latin1')}")
         pdf.multi_cell(0, 10, f"Answer: {mcq['answer'].encode('latin1', 'replace').decode('latin1')}\n")
 
+    # Save the generated PDF to a temporary file
     with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_pdf:
         pdf.output(temp_pdf.name)
         pdf_path = temp_pdf.name
-    
+
     return pdf_path
 
 def create_error_pdf(message):
@@ -135,18 +136,18 @@ def create_error_pdf(message):
     pdf.cell(200, 10, "Error Report", ln=True, align="C")
     pdf.set_font("Arial", "", 12)
     pdf.multi_cell(0, 10, message.encode('latin1', 'replace').decode('latin1'))
-    
+
     with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_pdf:
         pdf.output(temp_pdf.name)
         error_pdf_path = temp_pdf.name
-    
+
     return error_pdf_path
 
 iface = gr.Interface(
     fn=transcribe,
     inputs=gr.Audio(type="filepath"),
-    outputs=gr.File(label="Download PDF with Notes or Error Report"),
-    title="Voice to Text Converter and Notes Generator",
+    outputs=gr.File(label="Download Exam Paper (PDF)"),
+    title="Voice to Text Converter and Exam Paper Generator",
 )
 
 iface.launch()