Spaces:
Runtime error
Runtime error
Delete app.py
Browse files
app.py
DELETED
@@ -1,77 +0,0 @@
|
|
1 |
-
!pip install transformers pyPDF2 torchaudio
|
2 |
-
|
3 |
-
!pip install pdfminer.six
|
4 |
-
|
5 |
-
!pip install datasets sentencepiece
|
6 |
-
|
7 |
-
from google.colab import drive
|
8 |
-
from transformers import pipeline
|
9 |
-
import PyPDF2
|
10 |
-
|
11 |
-
from pdfminer.high_level import extract_pages, extract_text
|
12 |
-
|
13 |
-
from pdfminer.layout import LTTextContainer, LTChar
|
14 |
-
|
15 |
-
drive.mount('/content/drive')
|
16 |
-
|
17 |
-
pdf_path = '/content/drive/MyDrive/Applied AI/Assessment_3/Article 11 Hidden Technical Debt in Machine Learning Systems.pdf'
|
18 |
-
|
19 |
-
summarization = pipeline ('summarization', model = "pszemraj/long-t5-tglobal-base-16384-book-summary")
|
20 |
-
|
21 |
-
# Open the PDF file
|
22 |
-
pdf_file = open(pdf_path, 'rb')
|
23 |
-
pdf_reader = PyPDF2.PdfReader(pdf_file)
|
24 |
-
|
25 |
-
# Extract text from the Abstract section
|
26 |
-
abstract_text = pdf_reader.pages[0].extract_text()
|
27 |
-
|
28 |
-
# Close the PDF file
|
29 |
-
pdf_file.close()
|
30 |
-
|
31 |
-
summary = summarization(abstract_text, max_length=13, min_length=10)[0]['summary_text']
|
32 |
-
|
33 |
-
print(summary)
|
34 |
-
|
35 |
-
!pip install --upgrade transformers sentencepiece datasets[audio]
|
36 |
-
|
37 |
-
import torch
|
38 |
-
|
39 |
-
import soundfile as sf
|
40 |
-
|
41 |
-
from IPython.display import Audio
|
42 |
-
|
43 |
-
from datasets import load_dataset
|
44 |
-
|
45 |
-
synthesiser = pipeline("text-to-speech", "facebook/mms-tts-eng")
|
46 |
-
|
47 |
-
TTS_Output = synthesiser(summary)
|
48 |
-
|
49 |
-
print(TTS_Output.keys())
|
50 |
-
|
51 |
-
|
52 |
-
audio_key = TTS_Output["audio"]
|
53 |
-
|
54 |
-
|
55 |
-
Audio(data=audio_key[0], rate=16000)
|
56 |
-
|
57 |
-
!pip install gradio==2.3.6
|
58 |
-
!pip install --upgrade typing-extensions
|
59 |
-
|
60 |
-
import gradio as gr
|
61 |
-
|
62 |
-
def summarize_pdf(pdf_path):
|
63 |
-
pdf_file = open(pdf_path, 'rb')
|
64 |
-
pdf_reader = PyPDF2.PdfReader(pdf_file)
|
65 |
-
abstract_text = pdf_reader.pages[0].extract_text()
|
66 |
-
summary = summarization(abstract_text, max_length=13, min_length=10)[0]['summary_text']
|
67 |
-
pdf_file.close()
|
68 |
-
return summary
|
69 |
-
|
70 |
-
iface = gr.Interface(
|
71 |
-
fn=summarize_pdf,
|
72 |
-
inputs= "file",
|
73 |
-
outputs="text",
|
74 |
-
live=True,
|
75 |
-
title="PDF Summarizer",
|
76 |
-
description="Upload a PDF with an abstract, and the model will generate a summary."
|
77 |
-
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|