Spaces:
Running
Running
File size: 1,655 Bytes
67c46fd |
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 |
from pathlib import Path
from typing import Iterable
from typing import List
from typing import Union
import sentencepiece as spm
from funasr_detach.tokenizer.abs_tokenizer import BaseTokenizer
from funasr_detach.register import tables
@tables.register("tokenizer_classes", "SentencepiecesTokenizer")
class SentencepiecesTokenizer(BaseTokenizer):
def __init__(self, bpemodel: Union[Path, str], **kwargs):
super().__init__(**kwargs)
self.bpemodel = str(bpemodel)
# NOTE(kamo):
# Don't build SentencePieceProcessor in __init__()
# because it's not picklable and it may cause following error,
# "TypeError: can't pickle SwigPyObject objects",
# when giving it as argument of "multiprocessing.Process()".
self.sp = None
def __repr__(self):
return f'{self.__class__.__name__}(model="{self.bpemodel}")'
def _build_sentence_piece_processor(self):
# Build SentencePieceProcessor lazily.
if self.sp is None:
self.sp = spm.SentencePieceProcessor()
self.sp.load(self.bpemodel)
def text2tokens(self, line: str) -> List[str]:
self._build_sentence_piece_processor()
return self.sp.EncodeAsPieces(line)
def tokens2text(self, tokens: Iterable[str]) -> str:
self._build_sentence_piece_processor()
return self.sp.DecodePieces(list(tokens))
def encode(self, line: str) -> List[int]:
self._build_sentence_piece_processor()
return self.sp.EncodeAsIds(line)
def decode(self, line: List[int]):
self._build_sentence_piece_processor()
return self.sp.DecodeIds(line)
|