Update app.py

app.py

@@ -2,16 +2,22 @@ import gradio as gr
 import requests
 from fpdf import FPDF
 import nltk
+import os
 from nltk.tokenize import sent_tokenize
 import random
-import os
 
-# Ensure nltk resources are downloaded
-nltk.download("punkt")
+# Attempt to download punkt tokenizer
+try:
+    nltk.download("punkt")
+except:
+    print("NLTK punkt tokenizer download failed. Using custom tokenizer.")
+
+# Custom fallback for sentence tokenization
+def custom_sent_tokenize(text):
+    return text.split(". ")
 
 # Function to send audio to Groq API and get transcription
 def transcribe(audio_path):
-    # Read audio file in binary mode
     with open(audio_path, "rb") as audio_file:
         audio_data = audio_file.read()
 
@@ -19,7 +25,6 @@ def transcribe(audio_path):
     headers = {
         "Authorization": "Bearer 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",  # Replace with your actual API key
     }
-
     files = {
         'file': ('audio.wav', audio_data, 'audio/wav'),
     }
@@ -29,7 +34,6 @@ def transcribe(audio_path):
         'language': 'en',
     }
 
-    # Send audio to Groq API
     response = requests.post(groq_api_endpoint, headers=headers, files=files, data=data)
 
     if response.status_code == 200:
@@ -41,16 +45,15 @@ def transcribe(audio_path):
         print(f"API Error: {error_msg}")
         return create_error_pdf(f"API Error: {error_msg}")
 
-# Function to generate notes and questions
 def generate_notes(transcript):
-    # Split transcript into sentences
-    sentences = sent_tokenize(transcript)
+    try:
+        sentences = sent_tokenize(transcript)
+    except LookupError:
+        sentences = custom_sent_tokenize(transcript)
 
-    # Generate long and short questions
     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]]
 
-    # Generate MCQs
     mcqs = []
     for sentence in sentences[:5]:
         mcq = {
@@ -60,38 +63,31 @@ def generate_notes(transcript):
         }
         mcqs.append(mcq)
 
-    # Create PDF
     pdf_path = create_pdf(transcript, long_questions, short_questions, mcqs)
     return pdf_path
 
-# Function to create a PDF for transcription and questions
 def create_pdf(transcript, long_questions, short_questions, mcqs):
     pdf = FPDF()
     pdf.add_page()
     
-    # Title
     pdf.set_font("Arial", "B", 16)
     pdf.cell(200, 10, "Transcription Notes", ln=True, align="C")
 
-    # Transcription
     pdf.set_font("Arial", "", 12)
     pdf.multi_cell(0, 10, f"Transcription:\n{transcript}\n\n")
 
-    # Long Questions
     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}\n")
 
-    # Short Questions
     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}\n")
 
-    # MCQs
     pdf.set_font("Arial", "B", 14)
     pdf.cell(200, 10, "Multiple Choice Questions (MCQs)", ln=True)
     pdf.set_font("Arial", "", 12)
@@ -101,13 +97,11 @@ def create_pdf(transcript, long_questions, short_questions, mcqs):
             pdf.multi_cell(0, 10, f"   - {option}")
         pdf.multi_cell(0, 10, f"Answer: {mcq['answer']}\n")
 
-    # Save PDF
     pdf_path = "/mnt/data/transcription_notes.pdf"
     pdf.output(pdf_path)
     
     return pdf_path
 
-# Function to create an error PDF
 def create_error_pdf(message):
     pdf = FPDF()
     pdf.add_page()
@@ -120,7 +114,6 @@ def create_error_pdf(message):
     pdf.output(error_pdf_path)
     return error_pdf_path
 
-# Gradio interface
 iface = gr.Interface(
     fn=transcribe,
     inputs=gr.Audio(type="filepath"),