# coding=utf-8
# Copyright 2021 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 Speech2Text2."""
import json
import os
from typing import Dict, List, Optional, Tuple
from ...tokenization_utils import PreTrainedTokenizer
from ...utils import logging
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {
"vocab_file": "vocab.json",
"tokenizer_config_file": "tokenizer_config.json",
}
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"facebook/s2t-wav2vec2-large-en-de": "https://huggingface.co/facebook/s2t-wav2vec2-large-en-de/resolve/main/vocab.json",
},
"tokenizer_config_file": {
"facebook/s2t-wav2vec2-large-en-de": "https://huggingface.co/facebook/s2t-wav2vec2-large-en-de/resolve/main/tokenizer_config.json",
},
}
# Speech2Text2 has no max input length
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {"facebook/s2t-wav2vec2-large-en-de": 1024}
[docs]class Speech2Text2Tokenizer(PreTrainedTokenizer):
"""
Constructs a Speech2Text2Tokenizer.
This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains some of the main methods.
Users should refer to the superclass for more information regarding such methods.
Args:
vocab_file (:obj:`str`):
File containing the vocabulary.
bos_token (:obj:`str`, `optional`, defaults to :obj:`"<s>"`):
The beginning of sentence token.
eos_token (:obj:`str`, `optional`, defaults to :obj:`"</s>"`):
The end of sentence token.
unk_token (:obj:`str`, `optional`, defaults to :obj:`"<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 (:obj:`str`, `optional`, defaults to :obj:`"<pad>"`):
The token used for padding, for example when batching sequences of different lengths.
**kwargs
Additional keyword arguments passed along to :class:`~transformers.PreTrainedTokenizer`
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
model_input_names = ["input_ids", "attention_mask"]
def __init__(self, vocab_file, bos_token="<s>", pad_token="<pad>", eos_token="</s>", unk_token="<unk>", **kwargs):
super().__init__(
unk_token=unk_token,
bos_token=bos_token,
eos_token=eos_token,
pad_token=pad_token,
**kwargs,
)
with open(vocab_file, encoding="utf-8") as vocab_handle:
self.encoder = json.load(vocab_handle)
self.decoder = {v: k for k, v in self.encoder.items()}
@property
def vocab_size(self) -> int:
return len(self.decoder)
def get_vocab(self) -> Dict:
return dict(self.encoder, **self.added_tokens_encoder)
def _tokenize(self, text, **kwargs):
raise NotImplementedError("Tokenization requires a bpe tokenization file, which is currently not available")
def _convert_token_to_id(self, token: str) -> int:
"""Converts a token (str) in an index (integer) using the vocab."""
return self.encoder.get(token, self.encoder.get(self.unk_token))
def _convert_id_to_token(self, index: int) -> str:
"""Converts an index (integer) in a token (str) using the vocab."""
result = self.decoder.get(index, self.unk_token)
return result
def convert_tokens_to_string(self, tokens: List[str]) -> str:
"""
Converts a list of output tokens into a single string.
"""
# combine tokens
string = " ".join(tokens)
# make sure @@ tokens are concatenated
string = "".join(string.split("@@ "))
return string
[docs] def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
if not os.path.isdir(save_directory):
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
return
vocab_file = os.path.join(
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
)
with open(vocab_file, "w", encoding="utf-8") as f:
f.write(json.dumps(self.encoder, ensure_ascii=False))
return (vocab_file,)