Update app.py

app.py

@@ -3,26 +3,26 @@ from transformers import T5ForConditionalGeneration, T5Tokenizer
 
 sentence = st.text_area("enter some text")
 
-model = T5ForConditionalGeneration.from_pretrained("Unbabel/gec-t5_small")
-tokenizer = T5Tokenizer.from_pretrained('t5-small')
+if sentence:
 
-tokenized_sentence = tokenizer('gec: ' + sentence, max_length=128, truncation=True, padding='max_length', return_tensors='pt')
-corrected_sentence = tokenizer.decode(
-    model.generate(
-        input_ids = tokenized_sentence.input_ids,
-        attention_mask = tokenized_sentence.attention_mask, 
-        max_length=128,
-        num_beams=5,
-        early_stopping=True,
-    )[0],
-    skip_special_tokens=True, 
-    clean_up_tokenization_spaces=True
-)
-print(corrected_sentence) # -> I like swimming.
+    model = T5ForConditionalGeneration.from_pretrained("t5-small")
+    tokenizer = T5Tokenizer.from_pretrained('t5-small')
 
+    tokenized_sentence = tokenizer('gec: ' + sentence, max_length=128, truncation=True, padding='max_length', return_tensors='pt')
+    corrected_sentence = tokenizer.decode(
+        model.generate(
+            input_ids = tokenized_sentence.input_ids,
+            attention_mask = tokenized_sentence.attention_mask, 
+            max_length=128,
+            num_beams=5,
+            early_stopping=True,
+        )[0],
+        skip_special_tokens=True, 
+        clean_up_tokenization_spaces=True
+    )
+    #print(corrected_sentence) # -> I like swimming.
 
-#if text:
-    #st.json(corrected_sentence)
+    st.json(corrected_sentence)