File size: 3,913 Bytes
46f7742 62b5660 46f7742 62b5660 46f7742 62b5660 46f7742 62b5660 46f7742 62b5660 46f7742 62b5660 46f7742 62b5660 46f7742 62b5660 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 |
import os
from typing import Optional, Tuple, List
from collections import OrderedDict
from torch.utils.data import Dataset
from transformers import PreTrainedTokenizer, AutoTokenizer
def load_vocab(vocab_file):
vocab = OrderedDict()
with open(vocab_file, "r", encoding="utf-8") as reader:
tokens = reader.readlines()
for index, token in enumerate(tokens):
token = token.rstrip("\n")
vocab[token] = index
return vocab
class CharTokenizer(PreTrainedTokenizer):
vocab_files_names = {"vocab_file": "vocab.txt"}
def __init__(
self,
vocab_file=None,
pad_token="[pad]",
unk_token="[unk]",
bos_token="[bos]",
eos_token="[eos]",
do_lower_case=False,
*args,
**kwargs
):
super().__init__(
pad_token=pad_token,
unk_token=unk_token,
bos_token=bos_token,
eos_token=eos_token,
do_lower_case=do_lower_case,
**kwargs
)
self.do_lower_case = do_lower_case
if not vocab_file or not os.path.isfile(vocab_file):
self.vocab = OrderedDict()
self.ids_to_tokens = OrderedDict()
else:
self.vocab = load_vocab(vocab_file)
self.ids_to_tokens = OrderedDict([(ids, tok) for tok, ids in self.vocab.items()])
def train(self, file_path):
vocab = set()
with open(file_path) as r:
for line in r:
word = line.strip()
if self.do_lower_case:
word = word.lower()
vocab |= set(word)
vocab = list(vocab)
vocab.sort()
special_tokens = [self.pad_token, self.unk_token, self.bos_token, self.eos_token]
vocab = special_tokens + vocab
for i, ch in enumerate(vocab):
self.vocab[ch] = i
self.ids_to_tokens = vocab
@property
def vocab_size(self):
return len(self.vocab)
def get_vocab(self):
return self.vocab
def _convert_token_to_id(self, token):
if self.do_lower_case:
token = token.lower()
return self.vocab.get(token, self.vocab[self.unk_token])
def _convert_id_to_token(self, index):
return self.ids_to_tokens[index]
def _tokenize(self, text):
if self.do_lower_case:
text = text.lower()
return list(text)
def convert_tokens_to_string(self, tokens):
return "".join(tokens)
def build_inputs_with_special_tokens(
self,
token_ids_0: List[int],
token_ids_1: Optional[List[int]] = None
) -> List[int]:
bos = [self.bos_token_id]
eos = [self.eos_token_id]
return bos + token_ids_0 + eos
def get_special_tokens_mask(
self,
token_ids_0: List[int],
token_ids_1: Optional[List[int]] = None
) -> List[int]:
return [1] + ([0] * len(token_ids_0)) + [1]
def create_token_type_ids_from_sequences(
self,
token_ids_0: List[int],
token_ids_1: Optional[List[int]] = None
) -> List[int]:
return (len(token_ids_0) + 2) * [0]
def save_vocabulary(
self,
save_directory: str,
filename_prefix: Optional[str] = None
) -> Tuple[str]:
assert os.path.isdir(save_directory)
vocab_file = os.path.join(
save_directory,
(filename_prefix + "-" if filename_prefix else "") +
self.vocab_files_names["vocab_file"]
)
index = 0
with open(vocab_file, "w", encoding="utf-8") as writer:
for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]):
assert index == token_index
writer.write(token + "\n")
index += 1
return (vocab_file,)
AutoTokenizer.register("char_tokenizer", CharTokenizer)
|