Update app.py

app.py

@@ -6,7 +6,6 @@ import os
 import tempfile
 from nltk.tokenize import sent_tokenize
 import random
-import re
 
 # Attempt to download punkt tokenizer
 try:
@@ -39,111 +38,68 @@ def transcribe(audio_path):
     if response.status_code == 200:
         result = response.json()
         transcript = result.get("text", "No transcription available.")
-        return generate_exam_paper(transcript)
+        return generate_notes(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_exam_paper(transcript):
+def generate_notes(transcript):
     try:
         sentences = sent_tokenize(transcript)
     except LookupError:
         sentences = custom_sent_tokenize(transcript)
 
-    # Extract important sentences for generating questions
-    important_sentences = get_important_sentences(sentences)
-    
-    # Generate exam-like questions
-    long_questions = generate_long_questions(important_sentences)
-    short_questions = generate_short_questions(important_sentences)
-    mcqs = generate_mcqs(important_sentences)
-
-    # Ensure there are exactly 2 long questions, 5 short questions, and 7 MCQs
-    long_questions = long_questions[:2]  # Limit to 2 long questions
-    short_questions = short_questions[:5]  # Limit to 5 short questions
-    mcqs = mcqs[:7]  # Limit to 7 MCQs
-
-    pdf_path = create_pdf(transcript, long_questions, short_questions, mcqs)
-    return pdf_path
+    long_questions = [f"What is meant by '{sentence}'?" for sentence in sentences[:5]]
+    short_questions = [f"Define '{sentence.split()[0]}'." for sentence in sentences[:5]]
 
-def get_important_sentences(sentences):
-    # Focus on sentences that are likely to contain key information (like facts or definitions)
-    important_sentences = []
-    for sentence in sentences:
-        # 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
-
-def generate_long_questions(important_sentences):
-    long_questions = []
-    for sentence in important_sentences[:2]:  # Limit to 2 long questions
-        long_questions.append(f"Explain the historical significance of '{sentence}'?")
-    return long_questions
-
-def generate_short_questions(important_sentences):
-    short_questions = []
-    for sentence in important_sentences[:5]:  # Limit to 5 short questions
-        # Use the first word of the sentence to create short questions
-        short_questions.append(f"What is the definition of '{sentence.split()[0]}'?")
-    return short_questions
-
-def generate_mcqs(important_sentences):
     mcqs = []
-    for sentence in important_sentences[:7]:  # Limit to 7 MCQs
-        # 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
+    for sentence in sentences[:5]:
         mcq = {
-            "question": f"What is '{correct_answer}' in the context of the sentence?",
-            "options": options,
-            "answer": correct_answer
+            "question": f"What is '{sentence.split()[0]}'?",
+            "options": [sentence.split()[0]] + random.sample(["Option 1", "Option 2", "Option 3"], 3),
+            "answer": sentence.split()[0]
         }
         mcqs.append(mcq)
-    return mcqs
+
+    pdf_path = create_pdf(transcript, long_questions, short_questions, mcqs)
+    return pdf_path
 
 def create_pdf(transcript, long_questions, short_questions, mcqs):
     pdf = FPDF()
     pdf.add_page()
-
+    
     pdf.set_font("Arial", "B", 16)
-    pdf.cell(200, 10, "Exam Paper: Transcription Notes", ln=True, align="C")
+    pdf.cell(200, 10, "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
     pdf.set_font("Arial", "B", 14)
     pdf.cell(200, 10, "Long Questions", ln=True)
     pdf.set_font("Arial", "", 12)
-    for i, question in enumerate(long_questions, 1):
-        pdf.multi_cell(0, 10, f"{i}. {question.encode('latin1', 'replace').decode('latin1')}\n")
+    for question in long_questions:
+        pdf.multi_cell(0, 10, f"- {question.encode('latin1', 'replace').decode('latin1')}\n")
 
-    # Add Short Questions Section
     pdf.set_font("Arial", "B", 14)
     pdf.cell(200, 10, "Short Questions", ln=True)
     pdf.set_font("Arial", "", 12)
-    for i, question in enumerate(short_questions, 1):
-        pdf.multi_cell(0, 10, f"{i}. {question.encode('latin1', 'replace').decode('latin1')}\n")
+    for question in short_questions:
+        pdf.multi_cell(0, 10, f"- {question.encode('latin1', 'replace').decode('latin1')}\n")
 
-    # 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 i, mcq in enumerate(mcqs, 1):
-        pdf.multi_cell(0, 10, f"{i}. {mcq['question'].encode('latin1', 'replace').decode('latin1')}")
+    for mcq in mcqs:
+        pdf.multi_cell(0, 10, f"Q: {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):
@@ -153,18 +109,18 @@ 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 Exam Paper (PDF)"),
-    title="Voice to Text Converter and Exam Paper Generator",
+    outputs=gr.File(label="Download PDF with Notes or Error Report"),
+    title="Voice to Text Converter and Notes Generator",
 )
 
 iface.launch()