o
    ¾e¦i´  ã                   @   s:   d Z ddlmZ dddœZG dd„ deƒZeZddgZd	S )
z$Tokenization classes for DistilBERT.é   )ÚBertTokenizerz	vocab.txtztokenizer.json)Ú
vocab_fileÚtokenizer_filec                       s0   e Zd ZddgZddœdef‡ fdd„Z‡  ZS )ÚDistilBertTokenizerÚ	input_idsÚattention_maskT)Údo_lower_caser   c                   s   t ƒ j|d|i|¤Ž dS )aË  
        Construct a DistilBERT tokenizer (backed by HuggingFace's tokenizers library). Based on WordPiece.

        This tokenizer inherits from [`BertTokenizer`] which contains most of the main methods. Users should refer to
        this superclass for more information regarding those methods.

        Args:
            do_lower_case (`bool`, *optional*, defaults to `True`):
                Whether or not to lowercase the input when tokenizing.
        r   N)ÚsuperÚ__init__)Úselfr   ÚargsÚkwargs©Ú	__class__© út/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/distilbert/tokenization_distilbert.pyr
      s   zDistilBertTokenizer.__init__)Ú__name__Ú
__module__Ú__qualname__Úmodel_input_namesÚboolr
   Ú__classcell__r   r   r   r   r      s     r   ÚDistilBertTokenizerFastN)Ú__doc__Úmodels.bert.tokenization_bertr   ÚVOCAB_FILES_NAMESr   r   Ú__all__r   r   r   r   Ú<module>   s   
