Update app.py

app.py

@@ -8,6 +8,9 @@ from transformers import AutoTokenizer
 m = from_pretrained_keras('sgonzalezsilot/FakeNews-Detection-Twitter-Thesis')
 # model = from_pretrained_keras("keras-io/cct")
 
+MODEL = "digitalepidemiologylab/covid-twitter-bert-v2"
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+
 def bert_encode(tokenizer,data,maximum_length) :
   input_ids = []
   attention_masks = []
@@ -29,18 +32,16 @@ def bert_encode(tokenizer,data,maximum_length) :
 
   return np.array(input_ids),np.array(attention_masks)
     
-train_encodings = tokenizer(train_texts, truncation=True, padding=True)
-test_encodings = tokenizer(test_texts, truncation=True, padding=True)
+# train_encodings = tokenizer(train_texts, truncation=True, padding=True)
+# test_encodings = tokenizer(test_texts, truncation=True, padding=True)
+
 
-MODEL = "digitalepidemiologylab/covid-twitter-bert-v2"
-tokenizer = AutoTokenizer.from_pretrained(MODEL)
 
-sentence_length = 110
-train_input_ids,train_attention_masks = bert_encode(tokenizer,train_texts,sentence_length)
-test_input_ids,test_attention_masks = bert_encode(tokenizer,test_texts,sentence_length)
     
 def get_news(input_text):
-  return sentiment(input_text)
+    sentence_length = 110
+    train_input_ids,train_attention_masks = bert_encode(tokenizer,input_text,sentence_length)    
+  return m([train_input_ids,train_attention_masks])
 
 iface = gr.Interface(fn = get_news, 
                      inputs = "text",