Create app.py

app.py

@@ -0,0 +1,37 @@
+import nltk
+from nltk.tokenize import sent_tokenize
+import re
+import stanfordnlp
+from bleu import list_bleu
+
+@st.cache(allow_output_mutation=True)
+def get_model():
+  nltk.download('punkt')
+  nltk.download('averaged_perceptron_tagger')
+  stanfordnlp.download('en')
+  stf_nlp = stanfordnlp.Pipeline(processors='tokenize,mwt,pos')
+  return stf_nlp
+  
+def truecasing(input_text):
+    # split the text into sentences
+    sentences = sent_tokenize(input_text, language='english')
+    # capitalize the sentences
+    sentences_capitalized = [s.capitalize() for s in sentences]
+    # join the capitalized sentences
+    text_truecase = re.sub(" (?=[\.,'!?:;])", "", ' '.join(sentences_capitalized))
+    # capitalize words according to part-of-speech tagging (POS)
+    doc = stf_nlp(text_truecase)
+    text_truecase =  ' '.join([w.text.capitalize() if w.upos in ["PROPN","NNS"] \
+                                                   else w.text for sent in doc.sentences \
+                               for w in sent.words])
+    text_truecase = re.sub(r'\s([?.!"](?:\s|$))', r'\1', text_truecase)
+    text_truecase = str(text_truecase)
+    text_truecase = text_truecase.replace(" ,", ",").replace(" -", "-").replace(" 's", "'s")
+    return text_truecase
+
+with st.form(key='my_form'):
+    prompt = st.text_area(label='Enter sentence', value=" ")
+    submit_button = st.form_submit_button(label='Submit')
+    if submit_button:
+      m = truecasing(prompt)
+      st.write(m)