Update app.py

app.py

@@ -4,7 +4,6 @@
 
 import gradio as gr
 import PyPDF2
-import pdfplumber
 from transformers import pipeline, AutoProcessor, AutoModel, AutoTokenizer
 from PyPDF2 import PdfReader
 import torch
@@ -16,33 +15,43 @@ import io
 
 #Here is the code
 
-summarization = pipeline ('summarization', model = "pszemraj/long-t5-tglobal-base-16384-book-summary")
+summarization = pipeline('summarization', model='pszemraj/long-t5-tglobal-base-16384-book-summary')
 synthesiser = pipeline("text-to-speech", model='facebook/mms-tts-eng')
 
+def abstract_extract(uploaded_file):
+    pdf_bytes = BytesIO(uploaded_file)
+    pdf_reader = PyPDF2.PdfReader(pdf_bytes)
+    
+    abstract = ""
+    
+    for page_number in range(len(pdf_reader.pages)):
+        text = pdf_reader.pages[page_number].extract_text()
+        
+        if "abstract" in text.lower():
+            start_index = text.lower().find("abstract")  
+            end_index = text.lower().find("introduction")
+            abstract = text[start_index:end_index]
+            break
+    
+    return abstract
+
 def summarize_and_speech(pdf_file):
+    abstract_text = abstract_extract(pdf_file)
 
-    pdf_bytes_io = io.BytesIO(pdf_file)
-    pdf_reader = PyPDF2.PdfReader(pdf_bytes_io)
-    abstract_text = pdf_reader.pages[0].extract_text()
-    summary = summarization(abstract_text, max_length=13, min_length=10)[0]['summary_text']
-    print(summary)
+    summary = summarization(abstract_text, max_length=15, min_length=10)[0]['summary_text']
 
-    # Use a text-to-speech model to generate audio
-    synthesiser = pipeline("text-to-speech", model='facebook/mms-tts-eng')
     tts_output = synthesiser(summary)
-    print(tts_output)
     audio_data = tts_output[0]["audio"]
 
     return summary, audio_data
 
-
 iface = gr.Interface(
-    fn= summarize_and_speech,
+    fn=summarize_and_speech,
     inputs=gr.File(label="Upload PDF", type="binary"),
-    outputs=[gr.Textbox(label="Abstract Summary:"), gr.Audio(type="filepath", label="Summary_Speech")],
+    outputs=[gr.Textbox(label="Abstract Summary:"), gr.Audio(type="filepath", label="Summary Speech")],
     live=True,
-    title="Abstract_Research_Paper_Summarizer",
-    description="Upload a Research Paper PDF File. The model will generate a one line summary of the Abstract section and a speech audio.",
+    title="Abstract Research Paper Summarizer",
+    description="Upload a Research Paper PDF File. The model will generate a one line summary of the Abstract section and a speech audio."
 )
 
 iface.launch()