mirror of
https://github.com/Steffo99/unimore-bda-6.git
synced 2024-11-26 09:44:19 +00:00
27 lines
657 B
Python
27 lines
657 B
Python
|
import abc
|
||
|
|
import tokenizers
|
||
|
|
|
||
|
|
from .base import BaseTokenizer
|
||
|
|
|
||
|
|
|
||
|
|
class HuggingTokenizer(BaseTokenizer, metaclass=abc.ABCMeta):
|
||
|
|
def __init__(self):
|
||
|
|
super().__init__()
|
||
|
|
self.hug: tokenizers.Tokenizer = self._build_hugging_tokenizer()
|
||
|
|
|
||
|
|
def _build_hugging_tokenizer(self) -> tokenizers.Tokenizer:
|
||
|
|
raise NotImplementedError()
|
||
|
|
|
||
|
|
def tokenize_plain(self, text: str) -> str:
|
||
|
|
return " ".join(self.hug.encode(text).tokens)
|
||
|
|
|
||
|
|
|
||
|
|
class HuggingBertTokenizer(HuggingTokenizer):
|
||
|
|
def _build_hugging_tokenizer(self):
|
||
|
|
return tokenizers.Tokenizer.from_pretrained("bert-base-cased")
|
||
|
|
|
||
|
|
|
||
|
|
__all__ = (
|
||
|
|
"HuggingBertTokenizer",
|
||
|
|
)
|