image-match/python/py/Lib/site-packages/transformers/models/speecht5/tokenization_speecht5.py

# Copyright 2023 The Facebook Inc. and The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Tokenization class for SpeechT5."""

from typing import Any

from ...tokenization_utils_sentencepiece import SentencePieceBackend
from ...utils import logging
from ...utils.import_utils import requires
from .number_normalizer import EnglishNumberNormalizer


logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {"vocab_file": "spm_char.model"}


@requires(backends=("sentencepiece",))
class SpeechT5Tokenizer(SentencePieceBackend):
    """
    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 `"<s>"`):
            The begin of sequence token.
        eos_token (`str`, *optional*, defaults to `"</s>"`):
            The end of sequence token.
        unk_token (`str`, *optional*, defaults to `"<unk>"`):
            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 `"<pad>"`):
            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).
    """

    vocab_files_names = VOCAB_FILES_NAMES
    model_input_names = ["input_ids", "attention_mask"]
    is_fast = False

    def __init__(
        self,
        vocab_file,
        bos_token="<s>",
        eos_token="</s>",
        unk_token="<unk>",
        pad_token="<pad>",
        normalize=False,
        sp_model_kwargs: dict[str, Any] | None = None,
        **kwargs,
    ) -> None:
        self.normalize = normalize
        self._normalizer = None

        # Prepare sp_model_kwargs for parent class
        if sp_model_kwargs is not None:
            kwargs["sp_model_kwargs"] = sp_model_kwargs

        # Call parent init (which will load sp_model)
        super().__init__(
            vocab_file=vocab_file,
            bos_token=bos_token,
            eos_token=eos_token,
            unk_token=unk_token,
            pad_token=pad_token,
            normalize=normalize,
            **kwargs,
        )

    def prepare_for_tokenization(self, text, is_split_into_words=False, **kwargs):
        normalize = kwargs.pop("normalize", self.normalize)
        if is_split_into_words:
            text = " " + text
        if normalize:
            text = self.normalizer(text)
        return (text, kwargs)

    @property
    def normalizer(self):
        if self._normalizer is None:
            self._normalizer = EnglishNumberNormalizer()
        return self._normalizer

    @normalizer.setter
    def normalizer(self, value):
        self._normalizer = value

    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None) -> list[int]:
        """Build model inputs from a sequence by appending eos_token_id."""
        if token_ids_1 is None:
            return token_ids_0 + [self.eos_token_id]
        # We don't expect to process pairs, but leave the pair logic for API consistency
        return token_ids_0 + token_ids_1 + [self.eos_token_id]

    def get_special_tokens_mask(
        self, token_ids_0: list[int], token_ids_1: list[int] | None = None, already_has_special_tokens: bool = False
    ) -> list[int]:
        if already_has_special_tokens:
            return super().get_special_tokens_mask(
                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
            )

        suffix_ones = [1]
        if token_ids_1 is None:
            return ([0] * len(token_ids_0)) + suffix_ones
        return ([0] * len(token_ids_0)) + ([0] * len(token_ids_1)) + suffix_ones

    def create_token_type_ids_from_sequences(
        self, token_ids_0: list[int], token_ids_1: list[int] | None = None
    ) -> list[int]:
        """
        Create a mask from the two sequences passed to be used in a sequence-pair classification task. SpeechT5 does not
        make use of token type ids, therefore a list of zeros is returned.

        Args:
            token_ids_0 (`list[int]`):
                List of IDs.
            token_ids_1 (`list[int]`, *optional*):
                Optional second list of IDs for sequence pairs.

        Returns:
            `list[int]`: List of zeros.
        """
        eos = [self.eos_token_id]
        if token_ids_1 is None:
            return len(token_ids_0 + eos) * [0]
        return len(token_ids_0 + token_ids_1 + eos) * [0]


__all__ = ["SpeechT5Tokenizer"]