tj d Z ddlmZ ddlmZ ddlmZ ddlmZ ddl m
Z
ej e Z
d d
iZ ed G d
de ZdgZdS )z Tokenization class for SpeechT5. )Any )SentencePieceBackend)logging)requires )EnglishNumberNormalizer
vocab_filezspm_char.model)
sentencepiece)backendsc
D e Zd ZdZeZddgZdZ dd
ee e
f d z d d f fd
Z dd
Z e
d Zej d Zdd ee fdZ ddee dee d z ded ee f fd
Z ddee dee d z d ee fdZ xZS )SpeechT5Tokenizera
Construct a SpeechT5 tokenizer. Based on [SentencePiece](https://github.com/google/sentencepiece).
This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
this superclass for more information regarding those methods.
Args:
vocab_file (`str`):
[SentencePiece](https://github.com/google/sentencepiece) file (generally has a *.spm* extension) that
contains the vocabulary necessary to instantiate a tokenizer.
bos_token (`str`, *optional*, defaults to `""`):
The begin of sequence token.
eos_token (`str`, *optional*, defaults to `""`):
The end of sequence 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.
normalize (`bool`, *optional*, defaults to `False`):
Whether to convert numeric quantities in the text to their spelt-out english counterparts.
sp_model_kwargs (`dict`, *optional*):
Will be passed to the `SentencePieceProcessor.__init__()` method. The [Python wrapper for
SentencePiece](https://github.com/google/sentencepiece/tree/master/python) can be used, among other things,
to set:
- `enable_sampling`: Enable subword regularization.
- `nbest_size`: Sampling parameters for unigram. Invalid for BPE-Dropout.
- `nbest_size = {0,1}`: No sampling is performed.
- `nbest_size > 1`: samples from the nbest_size results.
- `nbest_size < 0`: assuming that nbest_size is infinite and samples from the all hypothesis (lattice)
using forward-filtering-and-backward-sampling algorithm.
- `alpha`: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
BPE-dropout.
Attributes:
sp_model (`SentencePieceProcessor`):
The *SentencePiece* processor that is used for every conversion (string, tokens and IDs).
input_idsattention_maskF