Update app.py

app.py

@@ -1,3 +1,62 @@
+!pip install transformers pyPDF2 torchaudio
+
+!pip install pdfminer.six
+
+!pip install datasets sentencepiece
+
+from google.colab import drive
+from transformers import pipeline
+import PyPDF2
+
+from pdfminer.high_level import extract_pages, extract_text
+
+from pdfminer.layout import LTTextContainer, LTChar
+
+drive.mount('/content/drive')
+
+pdf_path = '/content/drive/MyDrive/Applied AI/Assessment_3/Article 11 Hidden Technical Debt in Machine Learning Systems.pdf'
+
+summarization = pipeline ('summarization', model = "pszemraj/long-t5-tglobal-base-16384-book-summary")
+
+# Open the PDF file
+pdf_file = open(pdf_path, 'rb')
+pdf_reader = PyPDF2.PdfReader(pdf_file)
+
+# Extract text from the Abstract section
+abstract_text = pdf_reader.pages[0].extract_text()
+
+# Close the PDF file
+pdf_file.close()
+
+summary = summarization(abstract_text, max_length=13, min_length=10)[0]['summary_text']
+
+print(summary)
+
+!pip install --upgrade transformers sentencepiece datasets[audio]
+
+import torch
+
+import soundfile as sf
+
+from IPython.display import Audio
+
+from datasets import load_dataset
+
+synthesiser = pipeline("text-to-speech", "facebook/mms-tts-eng")
+
+TTS_Output = synthesiser(summary)
+
+print(TTS_Output.keys())
+
+
+audio_key = TTS_Output["audio"]
+
+
+Audio(data=audio_key[0], rate=16000)
+
+!pip install gradio==2.3.6
+!pip install --upgrade typing-extensions
+
 import gradio as gr
 
 def summarize_pdf(pdf_path):