Update app.py
Browse files
app.py
CHANGED
@@ -52,8 +52,8 @@ import line_cor
|
|
52 |
import altair as alt
|
53 |
#pytesseract.pytesseract.tesseract_cmd = r"./Tesseract-OCR/tesseract.exe"
|
54 |
from PIL import Image
|
55 |
-
|
56 |
-
|
57 |
def read_pdf(file):
|
58 |
# images=pdf2image.convert_from_path(file)
|
59 |
# # print(type(images))
|
@@ -87,23 +87,23 @@ def read_pdf(file):
|
|
87 |
# all_page_text += text + " " #page.extractText()
|
88 |
# return all_page_text
|
89 |
st.title("NLP APPLICATION")
|
90 |
-
|
91 |
-
|
92 |
def text_analyzer(my_text):
|
93 |
nlp = spacy.load('en_core_web_sm')
|
94 |
docx = nlp(my_text)
|
95 |
# tokens = [ token.text for token in docx]
|
96 |
allData = [('"Token":{},\n"Lemma":{}'.format(token.text,token.lemma_))for token in docx ]
|
97 |
return allData
|
98 |
-
|
99 |
-
|
100 |
def load_models():
|
101 |
tokenizer = AutoTokenizer.from_pretrained('gpt2-large')
|
102 |
model = GPT2LMHeadModel.from_pretrained('gpt2-large')
|
103 |
return tokenizer, model
|
104 |
# Function For Extracting Entities
|
105 |
-
|
106 |
-
|
107 |
def entity_analyzer(my_text):
|
108 |
nlp = spacy.load('en_core_web_sm')
|
109 |
docx = nlp(my_text)
|
|
|
52 |
import altair as alt
|
53 |
#pytesseract.pytesseract.tesseract_cmd = r"./Tesseract-OCR/tesseract.exe"
|
54 |
from PIL import Image
|
55 |
+
@st.experimental_singleton
|
56 |
+
#@st.cache_resource(experimental_allow_widgets=True)
|
57 |
def read_pdf(file):
|
58 |
# images=pdf2image.convert_from_path(file)
|
59 |
# # print(type(images))
|
|
|
87 |
# all_page_text += text + " " #page.extractText()
|
88 |
# return all_page_text
|
89 |
st.title("NLP APPLICATION")
|
90 |
+
@st.experimental_singleton
|
91 |
+
#@st.cache_resource(experimental_allow_widgets=True)
|
92 |
def text_analyzer(my_text):
|
93 |
nlp = spacy.load('en_core_web_sm')
|
94 |
docx = nlp(my_text)
|
95 |
# tokens = [ token.text for token in docx]
|
96 |
allData = [('"Token":{},\n"Lemma":{}'.format(token.text,token.lemma_))for token in docx ]
|
97 |
return allData
|
98 |
+
@st.experimental_singleton
|
99 |
+
#@st.cache_resource(experimental_allow_widgets=True)
|
100 |
def load_models():
|
101 |
tokenizer = AutoTokenizer.from_pretrained('gpt2-large')
|
102 |
model = GPT2LMHeadModel.from_pretrained('gpt2-large')
|
103 |
return tokenizer, model
|
104 |
# Function For Extracting Entities
|
105 |
+
@st.experimental_singleton
|
106 |
+
#@st.cache_resource(experimental_allow_widgets=True)
|
107 |
def entity_analyzer(my_text):
|
108 |
nlp = spacy.load('en_core_web_sm')
|
109 |
docx = nlp(my_text)
|