File size: 29,095 Bytes
9231ab9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
# coding=utf-8
# Copyright 2021 The HuggingFace Inc. team.
#
# 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.
"""
 Feature extraction saving/loading class for common feature extractors.
"""

import copy
import json
import os
import warnings
from collections import UserDict
from typing import TYPE_CHECKING, Any, Dict, Optional, Tuple, Union

import numpy as np

from .dynamic_module_utils import custom_object_save
from .utils import (
    FEATURE_EXTRACTOR_NAME,
    PushToHubMixin,
    TensorType,
    add_model_info_to_auto_map,
    cached_file,
    copy_func,
    download_url,
    is_flax_available,
    is_jax_tensor,
    is_numpy_array,
    is_offline_mode,
    is_remote_url,
    is_tf_available,
    is_torch_available,
    is_torch_device,
    is_torch_dtype,
    logging,
    requires_backends,
)


if TYPE_CHECKING:
    if is_torch_available():
        import torch  # noqa


logger = logging.get_logger(__name__)

PreTrainedFeatureExtractor = Union["SequenceFeatureExtractor"]  # noqa: F821


class BatchFeature(UserDict):
    r"""
    Holds the output of the [`~SequenceFeatureExtractor.pad`] and feature extractor specific `__call__` methods.

    This class is derived from a python dictionary and can be used as a dictionary.

    Args:
        data (`dict`, *optional*):
            Dictionary of lists/arrays/tensors returned by the __call__/pad methods ('input_values', 'attention_mask',
            etc.).
        tensor_type (`Union[None, str, TensorType]`, *optional*):
            You can give a tensor_type here to convert the lists of integers in PyTorch/TensorFlow/Numpy Tensors at
            initialization.
    """

    def __init__(self, data: Optional[Dict[str, Any]] = None, tensor_type: Union[None, str, TensorType] = None):
        super().__init__(data)
        self.convert_to_tensors(tensor_type=tensor_type)

    def __getitem__(self, item: str) -> Union[Any]:
        """
        If the key is a string, returns the value of the dict associated to `key` ('input_values', 'attention_mask',
        etc.).
        """
        if isinstance(item, str):
            return self.data[item]
        else:
            raise KeyError("Indexing with integers is not available when using Python based feature extractors")

    def __getattr__(self, item: str):
        try:
            return self.data[item]
        except KeyError:
            raise AttributeError

    def __getstate__(self):
        return {"data": self.data}

    def __setstate__(self, state):
        if "data" in state:
            self.data = state["data"]

    # Copied from transformers.tokenization_utils_base.BatchEncoding.keys
    def keys(self):
        return self.data.keys()

    # Copied from transformers.tokenization_utils_base.BatchEncoding.values
    def values(self):
        return self.data.values()

    # Copied from transformers.tokenization_utils_base.BatchEncoding.items
    def items(self):
        return self.data.items()

    def convert_to_tensors(self, tensor_type: Optional[Union[str, TensorType]] = None):
        """
        Convert the inner content to tensors.

        Args:
            tensor_type (`str` or [`~utils.TensorType`], *optional*):
                The type of tensors to use. If `str`, should be one of the values of the enum [`~utils.TensorType`]. If
                `None`, no modification is done.
        """
        if tensor_type is None:
            return self

        # Convert to TensorType
        if not isinstance(tensor_type, TensorType):
            tensor_type = TensorType(tensor_type)

        # Get a function reference for the correct framework
        if tensor_type == TensorType.TENSORFLOW:
            if not is_tf_available():
                raise ImportError(
                    "Unable to convert output to TensorFlow tensors format, TensorFlow is not installed."
                )
            import tensorflow as tf

            as_tensor = tf.constant
            is_tensor = tf.is_tensor
        elif tensor_type == TensorType.PYTORCH:
            if not is_torch_available():
                raise ImportError("Unable to convert output to PyTorch tensors format, PyTorch is not installed.")
            import torch  # noqa

            def as_tensor(value):
                if isinstance(value, (list, tuple)) and len(value) > 0 and isinstance(value[0], np.ndarray):
                    value = np.array(value)
                return torch.tensor(value)

            is_tensor = torch.is_tensor
        elif tensor_type == TensorType.JAX:
            if not is_flax_available():
                raise ImportError("Unable to convert output to JAX tensors format, JAX is not installed.")
            import jax.numpy as jnp  # noqa: F811

            as_tensor = jnp.array
            is_tensor = is_jax_tensor
        else:

            def as_tensor(value, dtype=None):
                if isinstance(value, (list, tuple)) and isinstance(value[0], (list, tuple, np.ndarray)):
                    value_lens = [len(val) for val in value]
                    if len(set(value_lens)) > 1 and dtype is None:
                        # we have a ragged list so handle explicitly
                        value = as_tensor([np.asarray(val) for val in value], dtype=object)
                return np.asarray(value, dtype=dtype)

            is_tensor = is_numpy_array

        # Do the tensor conversion in batch
        for key, value in self.items():
            try:
                if not is_tensor(value):
                    tensor = as_tensor(value)

                    self[key] = tensor
            except:  # noqa E722
                if key == "overflowing_values":
                    raise ValueError("Unable to create tensor returning overflowing values of different lengths. ")
                raise ValueError(
                    "Unable to create tensor, you should probably activate padding "
                    "with 'padding=True' to have batched tensors with the same length."
                )

        return self

    def to(self, *args, **kwargs) -> "BatchFeature":
        """
        Send all values to device by calling `v.to(*args, **kwargs)` (PyTorch only). This should support casting in
        different `dtypes` and sending the `BatchFeature` to a different `device`.

        Args:
            args (`Tuple`):
                Will be passed to the `to(...)` function of the tensors.
            kwargs (`Dict`, *optional*):
                Will be passed to the `to(...)` function of the tensors.

        Returns:
            [`BatchFeature`]: The same instance after modification.
        """
        requires_backends(self, ["torch"])
        import torch  # noqa

        new_data = {}
        device = kwargs.get("device")
        # Check if the args are a device or a dtype
        if device is None and len(args) > 0:
            # device should be always the first argument
            arg = args[0]
            if is_torch_dtype(arg):
                # The first argument is a dtype
                pass
            elif isinstance(arg, str) or is_torch_device(arg) or isinstance(arg, int):
                device = arg
            else:
                # it's something else
                raise ValueError(f"Attempting to cast a BatchFeature to type {str(arg)}. This is not supported.")
        # We cast only floating point tensors to avoid issues with tokenizers casting `LongTensor` to `FloatTensor`
        for k, v in self.items():
            # check if v is a floating point
            if torch.is_floating_point(v):
                # cast and send to device
                new_data[k] = v.to(*args, **kwargs)
            elif device is not None:
                new_data[k] = v.to(device=device)
            else:
                new_data[k] = v
        self.data = new_data
        return self


class FeatureExtractionMixin(PushToHubMixin):
    """
    This is a feature extraction mixin used to provide saving/loading functionality for sequential and image feature
    extractors.
    """

    _auto_class = None

    def __init__(self, **kwargs):
        """Set elements of `kwargs` as attributes."""
        # Pop "processor_class" as it should be saved as private attribute
        self._processor_class = kwargs.pop("processor_class", None)
        # Additional attributes without default values
        for key, value in kwargs.items():
            try:
                setattr(self, key, value)
            except AttributeError as err:
                logger.error(f"Can't set {key} with value {value} for {self}")
                raise err

    def _set_processor_class(self, processor_class: str):
        """Sets processor class as an attribute."""
        self._processor_class = processor_class

    @classmethod
    def from_pretrained(
        cls,
        pretrained_model_name_or_path: Union[str, os.PathLike],
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        local_files_only: bool = False,
        token: Optional[Union[str, bool]] = None,
        revision: str = "main",
        **kwargs,
    ):
        r"""
        Instantiate a type of [`~feature_extraction_utils.FeatureExtractionMixin`] from a feature extractor, *e.g.* a
        derived class of [`SequenceFeatureExtractor`].

        Args:
            pretrained_model_name_or_path (`str` or `os.PathLike`):
                This can be either:

                - a string, the *model id* of a pretrained feature_extractor hosted inside a model repo on
                  huggingface.co. Valid model ids can be located at the root-level, like `bert-base-uncased`, or
                  namespaced under a user or organization name, like `dbmdz/bert-base-german-cased`.
                - a path to a *directory* containing a feature extractor file saved using the
                  [`~feature_extraction_utils.FeatureExtractionMixin.save_pretrained`] method, e.g.,
                  `./my_model_directory/`.
                - a path or url to a saved feature extractor JSON *file*, e.g.,
                  `./my_model_directory/preprocessor_config.json`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model feature extractor should be cached if the
                standard cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force to (re-)download the feature extractor files and override the cached versions
                if they exist.
            resume_download (`bool`, *optional*, defaults to `False`):
                Whether or not to delete incompletely received file. Attempts to resume the download if such a file
                exists.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
            token (`str` or `bool`, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, or not specified, will use
                the token generated when running `huggingface-cli login` (stored in `~/.huggingface`).
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                identifier allowed by git.


                <Tip>

                To test a pull request you made on the Hub, you can pass `revision="refs/pr/<pr_number>".

                </Tip>

            return_unused_kwargs (`bool`, *optional*, defaults to `False`):
                If `False`, then this function returns just the final feature extractor object. If `True`, then this
                functions returns a `Tuple(feature_extractor, unused_kwargs)` where *unused_kwargs* is a dictionary
                consisting of the key/value pairs whose keys are not feature extractor attributes: i.e., the part of
                `kwargs` which has not been used to update `feature_extractor` and is otherwise ignored.
            kwargs (`Dict[str, Any]`, *optional*):
                The values in kwargs of any keys which are feature extractor attributes will be used to override the
                loaded values. Behavior concerning key/value pairs whose keys are *not* feature extractor attributes is
                controlled by the `return_unused_kwargs` keyword parameter.

        Returns:
            A feature extractor of type [`~feature_extraction_utils.FeatureExtractionMixin`].

        Examples:

        ```python
        # We can't instantiate directly the base class *FeatureExtractionMixin* nor *SequenceFeatureExtractor* so let's show the examples on a
        # derived class: *Wav2Vec2FeatureExtractor*
        feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(
            "facebook/wav2vec2-base-960h"
        )  # Download feature_extraction_config from huggingface.co and cache.
        feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(
            "./test/saved_model/"
        )  # E.g. feature_extractor (or model) was saved using *save_pretrained('./test/saved_model/')*
        feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("./test/saved_model/preprocessor_config.json")
        feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(
            "facebook/wav2vec2-base-960h", return_attention_mask=False, foo=False
        )
        assert feature_extractor.return_attention_mask is False
        feature_extractor, unused_kwargs = Wav2Vec2FeatureExtractor.from_pretrained(
            "facebook/wav2vec2-base-960h", return_attention_mask=False, foo=False, return_unused_kwargs=True
        )
        assert feature_extractor.return_attention_mask is False
        assert unused_kwargs == {"foo": False}
        ```"""
        kwargs["cache_dir"] = cache_dir
        kwargs["force_download"] = force_download
        kwargs["local_files_only"] = local_files_only
        kwargs["revision"] = revision

        use_auth_token = kwargs.pop("use_auth_token", None)
        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.", FutureWarning
            )
            if token is not None:
                raise ValueError(
                    "`token` and `use_auth_token` are both specified. Please set only the argument `token`."
                )
            token = use_auth_token

        if token is not None:
            kwargs["token"] = token

        feature_extractor_dict, kwargs = cls.get_feature_extractor_dict(pretrained_model_name_or_path, **kwargs)

        return cls.from_dict(feature_extractor_dict, **kwargs)

    def save_pretrained(self, save_directory: Union[str, os.PathLike], push_to_hub: bool = False, **kwargs):
        """
        Save a feature_extractor object to the directory `save_directory`, so that it can be re-loaded using the
        [`~feature_extraction_utils.FeatureExtractionMixin.from_pretrained`] class method.

        Args:
            save_directory (`str` or `os.PathLike`):
                Directory where the feature extractor JSON file will be saved (will be created if it does not exist).
            push_to_hub (`bool`, *optional*, defaults to `False`):
                Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
                repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                namespace).
            kwargs (`Dict[str, Any]`, *optional*):
                Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
        """
        use_auth_token = kwargs.pop("use_auth_token", None)

        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.", FutureWarning
            )
            if kwargs.get("token", None) is not None:
                raise ValueError(
                    "`token` and `use_auth_token` are both specified. Please set only the argument `token`."
                )
            kwargs["token"] = use_auth_token

        if os.path.isfile(save_directory):
            raise AssertionError(f"Provided path ({save_directory}) should be a directory, not a file")

        os.makedirs(save_directory, exist_ok=True)

        if push_to_hub:
            commit_message = kwargs.pop("commit_message", None)
            repo_id = kwargs.pop("repo_id", save_directory.split(os.path.sep)[-1])
            repo_id = self._create_repo(repo_id, **kwargs)
            files_timestamps = self._get_files_timestamps(save_directory)

        # If we have a custom config, we copy the file defining it in the folder and set the attributes so it can be
        # loaded from the Hub.
        if self._auto_class is not None:
            custom_object_save(self, save_directory, config=self)

        # If we save using the predefined names, we can load using `from_pretrained`
        output_feature_extractor_file = os.path.join(save_directory, FEATURE_EXTRACTOR_NAME)

        self.to_json_file(output_feature_extractor_file)
        logger.info(f"Feature extractor saved in {output_feature_extractor_file}")

        if push_to_hub:
            self._upload_modified_files(
                save_directory,
                repo_id,
                files_timestamps,
                commit_message=commit_message,
                token=kwargs.get("token"),
            )

        return [output_feature_extractor_file]

    @classmethod
    def get_feature_extractor_dict(
        cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs
    ) -> Tuple[Dict[str, Any], Dict[str, Any]]:
        """
        From a `pretrained_model_name_or_path`, resolve to a dictionary of parameters, to be used for instantiating a
        feature extractor of type [`~feature_extraction_utils.FeatureExtractionMixin`] using `from_dict`.

        Parameters:
            pretrained_model_name_or_path (`str` or `os.PathLike`):
                The identifier of the pre-trained checkpoint from which we want the dictionary of parameters.

        Returns:
            `Tuple[Dict, Dict]`: The dictionary(ies) that will be used to instantiate the feature extractor object.
        """
        cache_dir = kwargs.pop("cache_dir", None)
        force_download = kwargs.pop("force_download", False)
        resume_download = kwargs.pop("resume_download", False)
        proxies = kwargs.pop("proxies", None)
        token = kwargs.pop("token", None)
        use_auth_token = kwargs.pop("use_auth_token", None)
        local_files_only = kwargs.pop("local_files_only", False)
        revision = kwargs.pop("revision", None)

        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.", FutureWarning
            )
            if token is not None:
                raise ValueError(
                    "`token` and `use_auth_token` are both specified. Please set only the argument `token`."
                )
            token = use_auth_token

        from_pipeline = kwargs.pop("_from_pipeline", None)
        from_auto_class = kwargs.pop("_from_auto", False)

        user_agent = {"file_type": "feature extractor", "from_auto_class": from_auto_class}
        if from_pipeline is not None:
            user_agent["using_pipeline"] = from_pipeline

        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True

        pretrained_model_name_or_path = str(pretrained_model_name_or_path)
        is_local = os.path.isdir(pretrained_model_name_or_path)
        if os.path.isdir(pretrained_model_name_or_path):
            feature_extractor_file = os.path.join(pretrained_model_name_or_path, FEATURE_EXTRACTOR_NAME)
        if os.path.isfile(pretrained_model_name_or_path):
            resolved_feature_extractor_file = pretrained_model_name_or_path
            is_local = True
        elif is_remote_url(pretrained_model_name_or_path):
            feature_extractor_file = pretrained_model_name_or_path
            resolved_feature_extractor_file = download_url(pretrained_model_name_or_path)
        else:
            feature_extractor_file = FEATURE_EXTRACTOR_NAME
            try:
                # Load from local folder or from cache or download from model Hub and cache
                resolved_feature_extractor_file = cached_file(
                    pretrained_model_name_or_path,
                    feature_extractor_file,
                    cache_dir=cache_dir,
                    force_download=force_download,
                    proxies=proxies,
                    resume_download=resume_download,
                    local_files_only=local_files_only,
                    token=token,
                    user_agent=user_agent,
                    revision=revision,
                )
            except EnvironmentError:
                # Raise any environment error raise by `cached_file`. It will have a helpful error message adapted to
                # the original exception.
                raise
            except Exception:
                # For any other exception, we throw a generic error.
                raise EnvironmentError(
                    f"Can't load feature extractor for '{pretrained_model_name_or_path}'. If you were trying to load"
                    " it from 'https://huggingface.co/models', make sure you don't have a local directory with the"
                    f" same name. Otherwise, make sure '{pretrained_model_name_or_path}' is the correct path to a"
                    f" directory containing a {FEATURE_EXTRACTOR_NAME} file"
                )

        try:
            # Load feature_extractor dict
            with open(resolved_feature_extractor_file, "r", encoding="utf-8") as reader:
                text = reader.read()
            feature_extractor_dict = json.loads(text)

        except json.JSONDecodeError:
            raise EnvironmentError(
                f"It looks like the config file at '{resolved_feature_extractor_file}' is not a valid JSON file."
            )

        if is_local:
            logger.info(f"loading configuration file {resolved_feature_extractor_file}")
        else:
            logger.info(
                f"loading configuration file {feature_extractor_file} from cache at {resolved_feature_extractor_file}"
            )

        if "auto_map" in feature_extractor_dict and not is_local:
            feature_extractor_dict["auto_map"] = add_model_info_to_auto_map(
                feature_extractor_dict["auto_map"], pretrained_model_name_or_path
            )

        return feature_extractor_dict, kwargs

    @classmethod
    def from_dict(cls, feature_extractor_dict: Dict[str, Any], **kwargs) -> PreTrainedFeatureExtractor:
        """
        Instantiates a type of [`~feature_extraction_utils.FeatureExtractionMixin`] from a Python dictionary of
        parameters.

        Args:
            feature_extractor_dict (`Dict[str, Any]`):
                Dictionary that will be used to instantiate the feature extractor object. Such a dictionary can be
                retrieved from a pretrained checkpoint by leveraging the
                [`~feature_extraction_utils.FeatureExtractionMixin.to_dict`] method.
            kwargs (`Dict[str, Any]`):
                Additional parameters from which to initialize the feature extractor object.

        Returns:
            [`~feature_extraction_utils.FeatureExtractionMixin`]: The feature extractor object instantiated from those
            parameters.
        """
        return_unused_kwargs = kwargs.pop("return_unused_kwargs", False)

        feature_extractor = cls(**feature_extractor_dict)

        # Update feature_extractor with kwargs if needed
        to_remove = []
        for key, value in kwargs.items():
            if hasattr(feature_extractor, key):
                setattr(feature_extractor, key, value)
                to_remove.append(key)
        for key in to_remove:
            kwargs.pop(key, None)

        logger.info(f"Feature extractor {feature_extractor}")
        if return_unused_kwargs:
            return feature_extractor, kwargs
        else:
            return feature_extractor

    def to_dict(self) -> Dict[str, Any]:
        """
        Serializes this instance to a Python dictionary.

        Returns:
            `Dict[str, Any]`: Dictionary of all the attributes that make up this feature extractor instance.
        """
        output = copy.deepcopy(self.__dict__)
        output["feature_extractor_type"] = self.__class__.__name__

        return output

    @classmethod
    def from_json_file(cls, json_file: Union[str, os.PathLike]) -> PreTrainedFeatureExtractor:
        """
        Instantiates a feature extractor of type [`~feature_extraction_utils.FeatureExtractionMixin`] from the path to
        a JSON file of parameters.

        Args:
            json_file (`str` or `os.PathLike`):
                Path to the JSON file containing the parameters.

        Returns:
            A feature extractor of type [`~feature_extraction_utils.FeatureExtractionMixin`]: The feature_extractor
            object instantiated from that JSON file.
        """
        with open(json_file, "r", encoding="utf-8") as reader:
            text = reader.read()
        feature_extractor_dict = json.loads(text)
        return cls(**feature_extractor_dict)

    def to_json_string(self) -> str:
        """
        Serializes this instance to a JSON string.

        Returns:
            `str`: String containing all the attributes that make up this feature_extractor instance in JSON format.
        """
        dictionary = self.to_dict()

        for key, value in dictionary.items():
            if isinstance(value, np.ndarray):
                dictionary[key] = value.tolist()

        # make sure private name "_processor_class" is correctly
        # saved as "processor_class"
        _processor_class = dictionary.pop("_processor_class", None)
        if _processor_class is not None:
            dictionary["processor_class"] = _processor_class

        return json.dumps(dictionary, indent=2, sort_keys=True) + "\n"

    def to_json_file(self, json_file_path: Union[str, os.PathLike]):
        """
        Save this instance to a JSON file.

        Args:
            json_file_path (`str` or `os.PathLike`):
                Path to the JSON file in which this feature_extractor instance's parameters will be saved.
        """
        with open(json_file_path, "w", encoding="utf-8") as writer:
            writer.write(self.to_json_string())

    def __repr__(self):
        return f"{self.__class__.__name__} {self.to_json_string()}"

    @classmethod
    def register_for_auto_class(cls, auto_class="AutoFeatureExtractor"):
        """
        Register this class with a given auto class. This should only be used for custom feature extractors as the ones
        in the library are already mapped with `AutoFeatureExtractor`.

        <Tip warning={true}>

        This API is experimental and may have some slight breaking changes in the next releases.

        </Tip>

        Args:
            auto_class (`str` or `type`, *optional*, defaults to `"AutoFeatureExtractor"`):
                The auto class to register this new feature extractor with.
        """
        if not isinstance(auto_class, str):
            auto_class = auto_class.__name__

        import transformers.models.auto as auto_module

        if not hasattr(auto_module, auto_class):
            raise ValueError(f"{auto_class} is not a valid auto class.")

        cls._auto_class = auto_class


FeatureExtractionMixin.push_to_hub = copy_func(FeatureExtractionMixin.push_to_hub)
if FeatureExtractionMixin.push_to_hub.__doc__ is not None:
    FeatureExtractionMixin.push_to_hub.__doc__ = FeatureExtractionMixin.push_to_hub.__doc__.format(
        object="feature extractor", object_class="AutoFeatureExtractor", object_files="feature extractor file"
    )