| PRE_TRAINED_MODEL = 'bert-base-uncased' | |
| from transformers import BertTokenizer | |
| bert_tokenizer = BertTokenizer.from_pretrained(PRE_TRAINED_MODEL) | |
| id_data = 3 | |
| print('Kalimat:', raw_data.Text[id_data]) | |
| print('BERT Tokenizer:', bert_tokenizer.tokenize(data.Text[id_data])) |