Update app.py

app.py

@@ -28,34 +28,29 @@ def extract_abstract(pdf_bytes):
         return "Error in abstract extraction"
 
 def process_text(uploaded_file):
-    # Debugging: Print the type and path of the uploaded_file
-    print(f"Uploaded file type: {type(uploaded_file)}")
-    print(f"Uploaded file path: {uploaded_file}")
+    logging.debug(f"Uploaded file type: {type(uploaded_file)}")
+    logging.debug(f"Uploaded file content: {uploaded_file}")
 
-    # Read PDF file from the path
     try:
         with open(uploaded_file, "rb") as file:
             pdf_bytes = file.read()
     except Exception as e:
-        print(f"Error reading file from path: {e}")
+        logging.error(f"Error reading file from path: {e}")
         return "Error reading PDF file", None
 
     try:
         abstract_text = extract_abstract(pdf_bytes)
-        logging.info(f"Extracted abstract: {abstract_text[:200]}...")  # Log first 200 chars of abstract
+        logging.info(f"Extracted abstract: {abstract_text[:200]}...")
     except Exception as e:
         logging.error(f"Error in abstract extraction: {e}")
         return "Error in processing PDF", None
 
     try:
-        # Prepare inputs for the model
         inputs = tokenizer([abstract_text], max_length=1024, return_tensors='pt', truncation=True, padding="max_length")
-
-        # Generate summary
         summary_ids = model.generate(
             input_ids=inputs['input_ids'],
-            attention_mask=inputs['attention_mask'],  # Include attention mask
-            pad_token_id=model.config.pad_token_id,  # Include pad token id
+            attention_mask=inputs['attention_mask'],
+            pad_token_id=model.config.pad_token_id,
             num_beams=4,
             max_length=40,
             min_length=10,
@@ -65,30 +60,27 @@ def process_text(uploaded_file):
         )
         summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
 
-        # Post-process the summary
-        #words = summary.split()
-        #cleaned_summary = []
-        #for i, word in enumerate(words):
-        #    if '-' in word and i < len(words) - 1:
-        #        word = word.replace('-', '') + words[i + 1]
-        #        words[i + 1] = ""
+        words = summary.split()
+        cleaned_summary = []
+        for i, word in enumerate(words):
+            if '-' in word and i < len(words) - 1:
+                word = word.replace('-', '') + words[i + 1]
+                words[i + 1] = ""
 
-        #    if '.' in word and i != len(words) - 1:
-        #        word = word.replace('.', '')
-        #        cleaned_summary.append(word + ' and')
-        #    else:
-        #        cleaned_summary.append(word) 
+            if '.' in word and i != len(words) - 1:
+                word = word.replace('.', '')
+                cleaned_summary.append(word + ' and')
+            else:
+                cleaned_summary.append(word) 
 
         final_summary = ' '.join(cleaned_summary)
         final_summary = final_summary[0].upper() + final_summary[1:]
         final_summary = ' '.join(w[0].lower() + w[1:] if w.lower() != 'and' else w for w in final_summary.split())
 
-        # Convert summary to speech
         speech = synthesiser(final_summary, forward_params={"do_sample": True})
         audio_data = speech["audio"].squeeze()
         normalized_audio_data = np.int16(audio_data / np.max(np.abs(audio_data)) * 32767)
 
-        # Save audio to temporary file
         output_file = "temp_output.wav"
         scipy.io.wavfile.write(output_file, rate=speech["sampling_rate"], data=normalized_audio_data)