qi d Z ddlZddlmZmZmZmZmZ ddlm Z ddl
m Z ddl m
Z
e
j e Zdd d
Z G d d e Zd gZy)
z Tokenization class for model T5. N) Tokenizerdecoders normalizerspre_tokenizers
processors)Unigram )TokenizersBackend)loggingz spiece.modelztokenizer.json)
vocab_filetokenizer_filec p e Zd ZdZeZddgZeZ d de e
e e e f z dz f fd
Z
d Zd Z xZS )
T5Tokenizera
Construct a T5 tokenizer (backed by HuggingFace's *tokenizers* library). Based on
[Unigram](https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=unigram#models).
This tokenizer inherits from [`TokenizersBackend`] which contains most of the main methods. Users should
refer to this superclass for more information regarding those methods.
Args:
vocab_file (`str`, *optional*):
[SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that
contains the vocabulary necessary to instantiate a tokenizer.
eos_token (`str`, *optional*, defaults to `""`):
The end of sequence token.
When building a sequence using special tokens, this is not the token that is used for the end of sequence.
The token used is the `sep_token`.
unk_token (`str`, *optional*, defaults to `""`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead.
pad_token (`str`, *optional*, defaults to `""`):
The token used for padding, for example when batching sequences of different lengths.
extra_ids (`int`, *optional*, defaults to 100):
Add a number of extra ids added to the vocabulary for use as sentinels. These tokens are accessible as
"" where "{%d}" is a number between 0 and extra_ids-1. These tokens can be retrieved by
calling get_sentinel_tokens method and token ids can be by calling get_sentinel_token_ids method
additional_special_tokens (`list[str]`, *optional*):
Additional special tokens used by the tokenizer.
vocab (`str`, `dict` or `list`, *optional*):
Custom vocabulary dict. If not provided, a minimal vocabulary is created using the special tokens.
input_idsattention_maskNvocabc H || _ |q|D cg c] } dt | v s| }
} t |
dk r!|t | D cg c] } d| d
c} z
}nC|dkD r>|t |
k7 r0t d| d| d t | D cg c] } d| d
}
} |
}||| _ nbt | dft | dft | dfd g| _ t |dz
d
d
D ]# } | j
j
d| ddf % t t | j
d d
| _ |$t j | | j _ t j t j t j ddd g | j _ t% j ddd | j _ t) | T d|||||d| t- j. ddgg dd| j0 fg | j _ y c c} w c c} w c c} w )Nz
r zBoth extra_ids (z!) and additional_special_tokens (zk) are provided to T5Tokenizer. In this case the additional_special_tokens must include the extra_ids tokensg ) ▁g F)unk_id
byte_fallbackr alwaysT) replacementprepend_schemesplit) eos_token unk_token pad_token extra_idsadditional_special_tokens$A)r$ r% z$Br% )singlepairspecial_tokens )
_extra_idsstrlenrange
ValueError
_vocab_scoresappendr r
_tokenizerr Precompiled
normalizerr SequenceWhitespaceSplit Metaspace
pre_tokenizerr decodersuper__init__r TemplateProcessing eos_token_idpost_processor)
selfr r r r! _spm_precompiled_charsmapr" r# kwargsx extra_tokensi __class__s
X/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/t5/tokenization_t5.pyr: zT5Tokenizer.__init__G s_ $ % 0'@[!LTWXYTZDZA[L[< 1$)yIY-ZA
1#Q.?-ZZ)Q 9L0A#A &yk1RSlRm n 8=Y7GH!j1 -HLH(4 % !&D Y %Y %Y % "D 9q="b1
D""))Zs!+-**+ *
&m \-Z Is HH
H
H c T t t t d | j S )zQGet the list of sentinel tokens (extra_id tokens) from additional_special_tokens.c D t t j d| d uS )Nz)boolresearch)rA s rE z1T5Tokenizer.get_sentinel_tokens.. s bii0A1&E!Fd!R )listsetfilterr# )r> s rE get_sentinel_tokensz T5Tokenizer.get_sentinel_tokens s& RTXTrTrs t
rL c f | j D cg c] }| j | c}S c c}w )z&Get the token IDs for sentinel tokens.)rP convert_tokens_to_ids)r> tokens rE get_sentinel_token_idsz"T5Tokenizer.get_sentinel_token_ids s* ?C?W?W?YZe**51ZZZs .)Nr% zzNd N)__name__
__module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_namesmodel_input_namesr modelr+ rM tuplefloatr: rP rT
__classcell__)rD s @rE r r sl "H *$&67 E 7;"&"&K
T%U
+,,t3K
Z
[rL r )rY rI
tokenizersr r r r r tokenizers.modelsr tokenization_utils_tokenizersr
utilsr
get_loggerrV loggerrZ r __all__r) rL rE rh sW ' S S % >
H %#1EUV ~[# ~[B /rL