Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -1,18 +1,28 @@
|
|
1 |
import os
|
2 |
import PyPDF2
|
3 |
from PIL import Image
|
4 |
-
import
|
5 |
|
6 |
-
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
-
# Directory for storing extracted text from PDFs
|
10 |
-
text_directory = '/content/extracted_text'
|
11 |
|
12 |
-
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
14 |
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
os.makedirs(ocr_directory, exist_ok=True)
|
|
|
1 |
import os
|
2 |
import PyPDF2
|
3 |
from PIL import Image
|
4 |
+
import streamlit as st
|
5 |
|
6 |
+
def read_pdf(pdf):
|
7 |
+
reader=PyPDF2.PdfReader(pdf)
|
8 |
+
text=''
|
9 |
+
for page in reader.pages:
|
10 |
+
text+=page.extract_text()
|
11 |
+
# text_file_name = 'text.txt'
|
12 |
+
# text_file_path = '/content/text.txt'
|
13 |
+
# with open(text_file_path, 'w') as text_file:
|
14 |
+
# text_file.write(text)
|
15 |
+
return text
|
16 |
|
|
|
|
|
17 |
|
18 |
+
def summarizer(text):
|
19 |
+
model = T5ForConditionalGeneration.from_pretrained("t5-base")
|
20 |
+
tokenizer = T5TokenizerFast.from_pretrained("t5-base")
|
21 |
+
inputs = tokenizer.encode("summarize: " + text,return_tensors="pt", max_length=1000,truncation=True)
|
22 |
+
outputs = model.generate(inputs,max_length=1000, min_length=100,length_penalty=2.0, num_beams=4,early_stopping=True)
|
23 |
+
summary = tokenizer.decode(outputs[0])
|
24 |
+
return summary
|
25 |
|
26 |
+
|
27 |
+
st.title(':blue[Abstractive Summarizer]')
|
28 |
+
st.header('by: _Team_ _Rare_ _species_')
|
|