Spaces:
Sleeping
Sleeping
edithram23
commited on
Commit
•
908eafd
1
Parent(s):
67ff28f
Update app.py
Browse files
app.py
CHANGED
@@ -5,8 +5,10 @@ import fitz # PyMuPDF
|
|
5 |
from docx import Document
|
6 |
import re
|
7 |
import nltk
|
|
|
8 |
nltk.download('punkt')
|
9 |
|
|
|
10 |
def sentence_tokenize(text):
|
11 |
sentences = nltk.sent_tokenize(text)
|
12 |
return sentences
|
@@ -28,7 +30,6 @@ model_large = AutoModelForSeq2SeqLM.from_pretrained(model_dir_large)
|
|
28 |
# pattern = r'\[.*?\]'
|
29 |
# redacted_text = re.sub(pattern, '[redacted]', predicted_title)
|
30 |
# return redacted_text
|
31 |
-
from presidio_analyzer import AnalyzerEngine, PatternRecognizer, RecognizerResult, Pattern
|
32 |
|
33 |
# Initialize the analyzer engine
|
34 |
analyzer = AnalyzerEngine()
|
|
|
5 |
from docx import Document
|
6 |
import re
|
7 |
import nltk
|
8 |
+
from presidio_analyzer import AnalyzerEngine, PatternRecognizer, RecognizerResult, Pattern
|
9 |
nltk.download('punkt')
|
10 |
|
11 |
+
|
12 |
def sentence_tokenize(text):
|
13 |
sentences = nltk.sent_tokenize(text)
|
14 |
return sentences
|
|
|
30 |
# pattern = r'\[.*?\]'
|
31 |
# redacted_text = re.sub(pattern, '[redacted]', predicted_title)
|
32 |
# return redacted_text
|
|
|
33 |
|
34 |
# Initialize the analyzer engine
|
35 |
analyzer = AnalyzerEngine()
|