Updating colors

app.py

@@ -10,9 +10,11 @@ def inference(input_text):
     encoding = tokenizer.encode_ordinary(input_text)
     sentence = [tokenizer.decode([x]) for x in encoding]
     color_sentence = []
-    for word in sentence:
-        color_sentence.append((word, str(random.randint(0, 7))))
-    return len(encoding), color_sentence, encoding
+    color_encoding = []
+    for word, encode in zip(sentence, encoding):
+        color_sentence.append((word, str(encode)))
+        color_encoding.append((encode, str(encode)))
+    return len(encoding), color_sentence, color_encoding
 
 title = "Bilingual Tokenizer"
 description = "A simple Gradio interface to see tokenization of Hindi and English(Hinglish) text"