Update app.py

app.py

@@ -1,38 +1,38 @@
-import torch
-from transformers import PegasusForConditionalGeneration, PegasusTokenizer
+# import torch
+# from transformers import PegasusForConditionalGeneration, PegasusTokenizer
 
-model_name = 'tuner007/pegasus_paraphrase'
-torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
-tokenizer = PegasusTokenizer.from_pretrained(model_name)
-model = PegasusForConditionalGeneration.from_pretrained(model_name).to(torch_device)
+# model_name = 'tuner007/pegasus_paraphrase'
+# torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
+# tokenizer = PegasusTokenizer.from_pretrained(model_name)
+# model = PegasusForConditionalGeneration.from_pretrained(model_name).to(torch_device)
 
-def get_response(input_text,num_return_sequences):
-  batch = tokenizer.prepare_seq2seq_batch([input_text],truncation=True,padding='longest',max_length=60, return_tensors="pt").to(torch_device)
-  translated = model.generate(**batch,max_length=60,num_beams=10, num_return_sequences=num_return_sequences, temperature=1.5)
-  tgt_text = tokenizer.batch_decode(translated, skip_special_tokens=True)
-  return tgt_text
+# def get_response(input_text,num_return_sequences):
+#   batch = tokenizer.prepare_seq2seq_batch([input_text],truncation=True,padding='longest',max_length=60, return_tensors="pt").to(torch_device)
+#   translated = model.generate(**batch,max_length=60,num_beams=10, num_return_sequences=num_return_sequences, temperature=1.5)
+#   tgt_text = tokenizer.batch_decode(translated, skip_special_tokens=True)
+#   return tgt_text
 
-from sentence_splitter import SentenceSplitter, split_text_into_sentences
+# from sentence_splitter import SentenceSplitter, split_text_into_sentences
 
-splitter = SentenceSplitter(language='en')
+# splitter = SentenceSplitter(language='en')
 
-def paraphraze(text):
-  sentence_list = splitter.split(text)
-  paraphrase = []
+# def paraphraze(text):
+#   sentence_list = splitter.split(text)
+#   paraphrase = []
 
-  for i in sentence_list:
-    a = get_response(i,1)
-    paraphrase.append(a)
-    paraphrase2 = [' '.join(x) for x in paraphrase]
-    paraphrase3 = [' '.join(x for x in paraphrase2) ]
-  paraphrased_text = str(paraphrase3).strip('[]').strip("'")
-  return paraphrased_text
+#   for i in sentence_list:
+#     a = get_response(i,1)
+#     paraphrase.append(a)
+#     paraphrase2 = [' '.join(x) for x in paraphrase]
+#     paraphrase3 = [' '.join(x for x in paraphrase2) ]
+#   paraphrased_text = str(paraphrase3).strip('[]').strip("'")
+#   return paraphrased_text
 
 
-def summarize(text):
+# def summarize(text):
 
-  paraphrased_text = paraphraze(text)
-  return paraphrased_text
+#   paraphrased_text = paraphraze(text)
+#   return paraphrased_text
 ########################################################################################################
 
 import torch
@@ -73,6 +73,22 @@ def get_paraphrased_sentences(model, tokenizer, sentence, num_return_sequences=5
 import streamlit as st
 #from .paraphraser import get_paraphrased_sentences, model, tokenizer
 
+#######
+from sentence_splitter import SentenceSplitter, split_text_into_sentences
+
+splitter = SentenceSplitter(language='en')
+
+def clean(text):
+  sentence_list = splitter.split(text)
+  paraphrase = []
+
+  for i in sentence_list:
+    paraphrase.append(i)
+    paraphrase2 = [' '.join(x) for x in paraphrase]
+    paraphrase3 = [' '.join(x for x in paraphrase2) ]
+  paraphrased_text = str(paraphrase3).strip('[]').strip("'")
+  return paraphrased_text
+
 
 def app():
     st.title('Paraphraser')
@@ -84,17 +100,16 @@ def app():
     with col1:
         user_input = st.text_area('Enter text','', height=300)
         
-        #paraphraseNo = st.slider('Number of Parapharases',1,10,2)
+        paraphraseNo = st.slider('Number of Parapharases',1,10,2)
         if st.button('Paraphrase'):
             with st.spinner(text="This may take a moment..."):
-                
-                output = summarize(user_input)    
+                output = get_paraphrased_sentences(model, tokenizer, clean(user_input), num_beams=10, num_return_sequences=paraphraseNo)    
     
     #with spacer:
     
     with col2:
         for x, element in enumerate(output):
-            user_output = st.text_area(label="", value=output, height=200 )
+            user_output = st.text_area(label="", value=output[x], height=200 )
 
 # st.markdown(
 #     '''<style>
@@ -104,5 +119,4 @@ def app():
 # )
 
 if __name__ == '__main__':
-	app()
-    
+	app()