Update app.py

app.py

@@ -114,22 +114,26 @@ def process_final_text(text):
     word_attributions = [(letter[i], score[i]) for i in range(0, len(letter))]
 
     # Paraphraser:
-    inp_text =  "paraphrase: " + X_test + " </s>"
-
-    encoding = para_tokenizer.encode_plus(inp_text,pad_to_max_length=True, return_tensors="pt")
-    input_ids, attention_masks = encoding["input_ids"], encoding["attention_mask"]
-
-    outputs = para_model.generate(
-    input_ids=input_ids, attention_mask=attention_masks,
-        max_length=256,
-        do_sample=True,
-        top_k=120,
-        top_p=0.95,
-        early_stopping=True,
-        num_return_sequences=5
-    )
+    batch = para_tokenizer(X_test, return_tensors='pt')
+    generated_ids = para_model.generate(batch['input_ids'])
+    para_list = para_tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
+
+    # inp_text =  "paraphrase: " + X_test + " </s>"
+
+    # encoding = para_tokenizer.encode_plus(inp_text,pad_to_max_length=True, return_tensors="pt")
+    # input_ids, attention_masks = encoding["input_ids"], encoding["attention_mask"]
+
+    # outputs = para_model.generate(
+    # input_ids=input_ids, attention_mask=attention_masks,
+    #     max_length=256,
+    #     do_sample=True,
+    #     top_k=120,
+    #     top_p=0.95,
+    #     early_stopping=True,
+    #     num_return_sequences=5
+    # )
     
-    para_list = [tokenizer.decode(output, skip_special_tokens=True,clean_up_tokenization_spaces=True) for output in outputs]
+    # para_list = [tokenizer.decode(output, skip_special_tokens=True,clean_up_tokenization_spaces=True) for output in outputs]
     
     return {"Resilience": float(scores.numpy()[1]), "Non-Resilience": float(scores.numpy()[0])},keywords,NER,word_attributions,para_list