Update app.py

app.py

@@ -28,17 +28,16 @@ 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
+    # Debugging: Print the type and contents of the uploaded_file
     print(f"Uploaded file type: {type(uploaded_file)}")
-    print(f"Uploaded file path: {uploaded_file}")
+    print(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}")
-        return "Error reading PDF file", None
+    # Check if uploaded_file is a dictionary with 'data' key
+    if isinstance(uploaded_file, dict) and 'data' in uploaded_file:
+        pdf_bytes = uploaded_file['data']
+    else:
+        print("Uploaded file is not in the expected format")
+        return "File content could not be retrieved", None
 
     try:
         abstract_text = extract_abstract(pdf_bytes)
@@ -48,14 +47,29 @@ def process_text(uploaded_file):
         return "Error in processing PDF", None
 
     try:
-        inputs = tokenizer([abstract_text], max_length=1024, return_tensors='pt', truncation=True)
-        summary_ids = model.generate(inputs['input_ids'], num_beams=4, max_length=40, min_length=10, length_penalty=2.0, early_stopping=True, no_repeat_ngram_size=2)
+        # 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
+            num_beams=4,
+            max_length=40,
+            min_length=10,
+            length_penalty=2.0,
+            early_stopping=True,
+            no_repeat_ngram_size=2
+        )
         summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
 
+        # Convert summary to speech
         speech = synthesiser(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)