def __init__(
self,
vocab_file,
do_lower_case=True,
do_basic_tokenize=True,
never_split=None,
unk_token="[UNK]",
sep_token="[SEP]",
pad_token="[PAD]",
cls_token="[CLS]",
mask_token="[MASK]",
tokenize_chinese_chars=True,
strip_accents=None,
**kwargs,
):
super().__init__(
do_lower_case=do_lower_case,
do_basic_tokenize=do_basic_tokenize,
never_split=never_split,
unk_token=unk_token,
sep_token=sep_token,
pad_token=pad_token,
cls_token=cls_token,
mask_token=mask_token,
tokenize_chinese_chars=tokenize_chinese_chars,
strip_accents=strip_accents,
**kwargs,
)
if not os.path.isfile(vocab_file):
raise ValueError(
f"Can't find a vocabulary file at path '{vocab_file}'. To load the vocabulary from a Google pretrained "
"model use `tokenizer = AutoTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`"
)
self.vocab = load_vocab(vocab_file)
self.ids_to_tokens = collections.OrderedDict([
(ids, tok) for tok, ids in self.vocab.items()
])
self.do_basic_tokenize = do_basic_tokenize
if do_basic_tokenize:
self.basic_tokenizer = BasicTokenizer(
do_lower_case=do_lower_case,
never_split=never_split,
tokenize_chinese_chars=tokenize_chinese_chars,
strip_accents=strip_accents,
)
self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab,
unk_token=self.unk_token)
try:
import rjieba
except ImportError:
raise ImportError(
"You need to install rjieba to use RoFormerTokenizer. "
"See https://pypi.org/project/rjieba/ for installation.")
self.jieba = rjieba
def __init__(self,
vocab_file,
do_lower_case=True,
do_basic_tokenize=True,
do_char_tokenize=False,
do_wordpiece_tokenize=False,
do_preprocessing=True,
unk_token='[UNK]',
sep_token='[SEP]',
pad_token='[PAD]',
cls_token='[CLS]',
mask_token='[MASK]',
**kwargs):
super(BertTokenizer, self).__init__(unk_token=unk_token,
sep_token=sep_token,
pad_token=pad_token,
cls_token=cls_token,
mask_token=mask_token,
**kwargs)
self.do_wordpiece_tokenize = do_wordpiece_tokenize
self.do_lower_case = do_lower_case
self.vocab_file = vocab_file
self.do_basic_tokenize = do_basic_tokenize
self.do_char_tokenize = do_char_tokenize
self.unk_token = unk_token
self.do_preprocessing = do_preprocessing
if not os.path.isfile(vocab_file):
raise ValueError(
"Can't find a vocabulary file at path '{}'.".format(
vocab_file))
self.vocab = load_vocab(vocab_file)
self.ids_to_tokens = collections.OrderedDict([
(ids, tok) for tok, ids in self.vocab.items()
])
if do_wordpiece_tokenize:
self.wordpiece_tokenizer = WordpieceTokenizer(
vocab=self.vocab, unk_token=self.unk_token)
self.base_bert_tok = BertTokenizer(vocab_file=self.vocab_file,
do_lower_case=do_lower_case,
unk_token=unk_token,
sep_token=sep_token,
pad_token=pad_token,
cls_token=cls_token,
mask_token=mask_token,
**kwargs)
def __init__(self,
vocab_file,
do_lower_case=True,
unk_token="[UNK]",
sep_token="[SEP]",
pad_token="[PAD]",
cls_token="[CLS]",
mask_token="[MASK]",
**kwargs):
"""
:param vocab_file: Path to a one-word-per-line vocabulary file
:type vocab_file: str
:param do_lower_case: Flag whether to lower case the input
:type do_lower_case: bool
"""
# TODO check why EmbeddingTokenizer.tokenize gives many UNK, while tokenize_with_metadata() works fine
super().__init__(
unk_token=unk_token,
sep_token=sep_token,
pad_token=pad_token,
cls_token=cls_token,
mask_token=mask_token,
**kwargs,
)
if not os.path.isfile(vocab_file):
raise ValueError(
"Can't find a vocabulary file at path '{}'.".format(
vocab_file))
self.vocab = load_vocab(vocab_file)
self.unk_tok_idx = self.vocab[unk_token]
self.ids_to_tokens = collections.OrderedDict([
(ids, tok) for tok, ids in self.vocab.items()
])
self.do_lower_case = do_lower_case