def test_ids_to_text(self): tokenizer = SentencePieceTokenizer("./tests/data/m_common.model") special_tokens = nemo_nlp.data.tokenizers.MODEL_SPECIAL_TOKENS['bert'] tokenizer.add_special_tokens(special_tokens) text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]" ids = tokenizer.text_to_ids(text) result = tokenizer.ids_to_text(ids) self.assertTrue(text == result)
def test_ids_to_text(self): tokenizer = SentencePieceTokenizer("./tests/data/m_common.model") special_tokens = ["[CLS]", "[MASK]", "[SEP]"] tokenizer.add_special_tokens(special_tokens) text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]" ids = tokenizer.text_to_ids(text) result = tokenizer.ids_to_text(ids) self.assertTrue(text == result)
def test_text_to_ids(self): tokenizer = SentencePieceTokenizer("./tests/data/m_common.model") special_tokens = nemo_nlp.data.tokenizers.MODEL_SPECIAL_TOKENS['bert'] tokenizer.add_special_tokens(special_tokens) text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]" ids = tokenizer.text_to_ids(text) self.assertTrue(len(ids) == len(text.split())) self.assertTrue(ids.count(tokenizer.token_to_id("[CLS]")) == 1) self.assertTrue(ids.count(tokenizer.token_to_id("[MASK]")) == 1) self.assertTrue(ids.count(tokenizer.token_to_id("[SEP]")) == 2)
def test_text_to_ids(self): tokenizer = SentencePieceTokenizer("./tests/data/m_common.model") special_tokens = ["[CLS]", "[MASK]", "[SEP]"] tokenizer.add_special_tokens(special_tokens) text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]" ids = tokenizer.text_to_ids(text) self.assertTrue(len(ids) == len(text.split())) self.assertTrue(ids.count(tokenizer.special_tokens["[CLS]"]) == 1) self.assertTrue(ids.count(tokenizer.special_tokens["[MASK]"]) == 1) self.assertTrue(ids.count(tokenizer.special_tokens["[SEP]"]) == 2)