Python SentencePieceTokenizer.ids_to_tokens 예제들

예제 #1

파일: test_spc_tokenizer.py 프로젝트: joehoeller/NVIDIA-Rapids-NeMo-PyTorch-Tensorboard

    def test_ids_to_tokens(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]"
        tokens = tokenizer.text_to_tokens(text)
        ids = tokenizer.tokens_to_ids(tokens)
        result = tokenizer.ids_to_tokens(ids)

        self.assertTrue(len(result) == len(tokens))

        for i in range(len(result)):
            self.assertTrue(result[i] == tokens[i])

예제 #2

파일: test_spc_tokenizer.py 프로젝트: phymucs/NeMo

    def test_ids_to_tokens(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]"
        tokens = tokenizer.text_to_tokens(text)
        ids = tokenizer.tokens_to_ids(tokens)
        result = tokenizer.ids_to_tokens(ids)

        self.assertTrue(len(result) == len(tokens))

        for i in range(len(result)):
            self.assertTrue(result[i] == tokens[i])