File size: 4,430 Bytes
6a62ffb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
"""isort:skip_file"""

from .dictionary import Dictionary, TruncatedDictionary

from .fairseq_dataset import FairseqDataset, FairseqIterableDataset

from .base_wrapper_dataset import BaseWrapperDataset

from .add_target_dataset import AddTargetDataset
from .append_token_dataset import AppendTokenDataset
from .audio.raw_audio_dataset import BinarizedAudioDataset, FileAudioDataset
from .audio.hubert_dataset import HubertDataset
from .backtranslation_dataset import BacktranslationDataset
from .bucket_pad_length_dataset import BucketPadLengthDataset
from .colorize_dataset import ColorizeDataset
from .concat_dataset import ConcatDataset
from .concat_sentences_dataset import ConcatSentencesDataset
from .denoising_dataset import DenoisingDataset
from .id_dataset import IdDataset
from .indexed_dataset import (
    IndexedCachedDataset,
    IndexedDataset,
    IndexedRawTextDataset,
    MMapIndexedDataset,
)
from .language_pair_dataset import LanguagePairDataset
from .list_dataset import ListDataset
from .lm_context_window_dataset import LMContextWindowDataset
from .lru_cache_dataset import LRUCacheDataset
from .mask_tokens_dataset import MaskTokensDataset
from .monolingual_dataset import MonolingualDataset
from .multi_corpus_sampled_dataset import MultiCorpusSampledDataset
from .nested_dictionary_dataset import NestedDictionaryDataset
from .noising import NoisingDataset
from .numel_dataset import NumelDataset
from .num_samples_dataset import NumSamplesDataset
from .offset_tokens_dataset import OffsetTokensDataset
from .pad_dataset import LeftPadDataset, PadDataset, RightPadDataset
from .prepend_dataset import PrependDataset
from .prepend_token_dataset import PrependTokenDataset
from .raw_label_dataset import RawLabelDataset
from .replace_dataset import ReplaceDataset
from .resampling_dataset import ResamplingDataset
from .roll_dataset import RollDataset
from .round_robin_zip_datasets import RoundRobinZipDatasets
from .sort_dataset import SortDataset
from .strip_token_dataset import StripTokenDataset
from .subsample_dataset import SubsampleDataset
from .token_block_dataset import TokenBlockDataset
from .transform_eos_dataset import TransformEosDataset
from .transform_eos_lang_pair_dataset import TransformEosLangPairDataset
from .shorten_dataset import TruncateDataset, RandomCropDataset
from .multilingual.sampled_multi_dataset import SampledMultiDataset
from .multilingual.sampled_multi_epoch_dataset import SampledMultiEpochDataset
from .fasta_dataset import FastaDataset, EncodedFastaDataset
from .transform_eos_concat_langpair_dataset import TransformEosConcatLangPairDataset

from .iterators import (
    CountingIterator,
    EpochBatchIterator,
    GroupedIterator,
    ShardedIterator,
)

__all__ = [
    "AddTargetDataset",
    "AppendTokenDataset",
    "BacktranslationDataset",
    "BaseWrapperDataset",
    "BinarizedAudioDataset",
    "BucketPadLengthDataset",
    "ColorizeDataset",
    "ConcatDataset",
    "ConcatSentencesDataset",
    "CountingIterator",
    "DenoisingDataset",
    "Dictionary",
    "EncodedFastaDataset",
    "EpochBatchIterator",
    "FairseqDataset",
    "FairseqIterableDataset",
    "FastaDataset",
    "FileAudioDataset",
    "GroupedIterator",
    "HubertDataset",
    "IdDataset",
    "IndexedCachedDataset",
    "IndexedDataset",
    "IndexedRawTextDataset",
    "LanguagePairDataset",
    "LeftPadDataset",
    "ListDataset",
    "LMContextWindowDataset",
    "LRUCacheDataset",
    "MaskTokensDataset",
    "MMapIndexedDataset",
    "MonolingualDataset",
    "MultiCorpusSampledDataset",
    "NestedDictionaryDataset",
    "NoisingDataset",
    "NumelDataset",
    "NumSamplesDataset",
    "OffsetTokensDataset",
    "PadDataset",
    "PrependDataset",
    "PrependTokenDataset",
    "RandomCropDataset",
    "RawLabelDataset",
    "ResamplingDataset",
    "ReplaceDataset",
    "RightPadDataset",
    "RollDataset",
    "RoundRobinZipDatasets",
    "SampledMultiDataset",
    "SampledMultiEpochDataset",
    "ShardedIterator",
    "SortDataset",
    "StripTokenDataset",
    "SubsampleDataset",
    "TokenBlockDataset",
    "TransformEosDataset",
    "TransformEosLangPairDataset",
    "TransformEosConcatLangPairDataset",
    "TruncateDataset",
    "TruncatedDictionary",
]