File size: 15,876 Bytes
1ce5e18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# 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.
""" AutoProcessor class."""
import importlib
import inspect
import json
import os
import warnings
from collections import OrderedDict

# Build the list of all feature extractors
from ...configuration_utils import PretrainedConfig
from ...dynamic_module_utils import get_class_from_dynamic_module, resolve_trust_remote_code
from ...feature_extraction_utils import FeatureExtractionMixin
from ...image_processing_utils import ImageProcessingMixin
from ...tokenization_utils import TOKENIZER_CONFIG_FILE
from ...utils import FEATURE_EXTRACTOR_NAME, get_file_from_repo, logging
from .auto_factory import _LazyAutoMapping
from .configuration_auto import (
    CONFIG_MAPPING_NAMES,
    AutoConfig,
    model_type_to_module_name,
    replace_list_option_in_docstrings,
)
from .feature_extraction_auto import AutoFeatureExtractor
from .image_processing_auto import AutoImageProcessor
from .tokenization_auto import AutoTokenizer


logger = logging.get_logger(__name__)

PROCESSOR_MAPPING_NAMES = OrderedDict(
    [
        ("align", "AlignProcessor"),
        ("altclip", "AltCLIPProcessor"),
        ("bark", "BarkProcessor"),
        ("blip", "BlipProcessor"),
        ("blip-2", "Blip2Processor"),
        ("bridgetower", "BridgeTowerProcessor"),
        ("chinese_clip", "ChineseCLIPProcessor"),
        ("clap", "ClapProcessor"),
        ("clip", "CLIPProcessor"),
        ("clipseg", "CLIPSegProcessor"),
        ("flava", "FlavaProcessor"),
        ("git", "GitProcessor"),
        ("groupvit", "CLIPProcessor"),
        ("hubert", "Wav2Vec2Processor"),
        ("idefics", "IdeficsProcessor"),
        ("instructblip", "InstructBlipProcessor"),
        ("layoutlmv2", "LayoutLMv2Processor"),
        ("layoutlmv3", "LayoutLMv3Processor"),
        ("markuplm", "MarkupLMProcessor"),
        ("mctct", "MCTCTProcessor"),
        ("mgp-str", "MgpstrProcessor"),
        ("oneformer", "OneFormerProcessor"),
        ("owlvit", "OwlViTProcessor"),
        ("pix2struct", "Pix2StructProcessor"),
        ("pop2piano", "Pop2PianoProcessor"),
        ("sam", "SamProcessor"),
        ("sew", "Wav2Vec2Processor"),
        ("sew-d", "Wav2Vec2Processor"),
        ("speech_to_text", "Speech2TextProcessor"),
        ("speech_to_text_2", "Speech2Text2Processor"),
        ("speecht5", "SpeechT5Processor"),
        ("trocr", "TrOCRProcessor"),
        ("tvlt", "TvltProcessor"),
        ("unispeech", "Wav2Vec2Processor"),
        ("unispeech-sat", "Wav2Vec2Processor"),
        ("vilt", "ViltProcessor"),
        ("vision-text-dual-encoder", "VisionTextDualEncoderProcessor"),
        ("wav2vec2", "Wav2Vec2Processor"),
        ("wav2vec2-conformer", "Wav2Vec2Processor"),
        ("wavlm", "Wav2Vec2Processor"),
        ("whisper", "WhisperProcessor"),
        ("xclip", "XCLIPProcessor"),
    ]
)

PROCESSOR_MAPPING = _LazyAutoMapping(CONFIG_MAPPING_NAMES, PROCESSOR_MAPPING_NAMES)


def processor_class_from_name(class_name: str):
    for module_name, processors in PROCESSOR_MAPPING_NAMES.items():
        if class_name in processors:
            module_name = model_type_to_module_name(module_name)

            module = importlib.import_module(f".{module_name}", "transformers.models")
            try:
                return getattr(module, class_name)
            except AttributeError:
                continue

    for processor in PROCESSOR_MAPPING._extra_content.values():
        if getattr(processor, "__name__", None) == class_name:
            return processor

    # We did not fine the class, but maybe it's because a dep is missing. In that case, the class will be in the main
    # init and we return the proper dummy to get an appropriate error message.
    main_module = importlib.import_module("transformers")
    if hasattr(main_module, class_name):
        return getattr(main_module, class_name)

    return None


class AutoProcessor:
    r"""
    This is a generic processor class that will be instantiated as one of the processor classes of the library when
    created with the [`AutoProcessor.from_pretrained`] class method.

    This class cannot be instantiated directly using `__init__()` (throws an error).
    """

    def __init__(self):
        raise EnvironmentError(
            "AutoProcessor is designed to be instantiated "
            "using the `AutoProcessor.from_pretrained(pretrained_model_name_or_path)` method."
        )

    @classmethod
    @replace_list_option_in_docstrings(PROCESSOR_MAPPING_NAMES)
    def from_pretrained(cls, pretrained_model_name_or_path, **kwargs):
        r"""
        Instantiate one of the processor classes of the library from a pretrained model vocabulary.

        The processor class to instantiate is selected based on the `model_type` property of the config object (either
        passed as an argument or loaded from `pretrained_model_name_or_path` if possible):

        List options

        Params:
            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 processor files saved using the `save_pretrained()` method,
                  e.g., `./my_model_directory/`.
            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`, 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.
            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.
            trust_remote_code (`bool`, *optional*, defaults to `False`):
                Whether or not to allow for custom models defined on the Hub in their own modeling files. This option
                should only be set to `True` for repositories you trust and in which you have read the code, as it will
                execute code present on the Hub on your local machine.
            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.

        <Tip>

        Passing `token=True` is required when you want to use a private model.

        </Tip>

        Examples:

        ```python
        >>> from transformers import AutoProcessor

        >>> # Download processor from huggingface.co and cache.
        >>> processor = AutoProcessor.from_pretrained("facebook/wav2vec2-base-960h")

        >>> # If processor files are in a directory (e.g. processor was saved using *save_pretrained('./test/saved_model/')*)
        >>> # processor = AutoProcessor.from_pretrained("./test/saved_model/")
        ```"""
        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

        config = kwargs.pop("config", None)
        trust_remote_code = kwargs.pop("trust_remote_code", None)
        kwargs["_from_auto"] = True

        processor_class = None
        processor_auto_map = None

        # First, let's see if we have a preprocessor config.
        # Filter the kwargs for `get_file_from_repo`.
        get_file_from_repo_kwargs = {
            key: kwargs[key] for key in inspect.signature(get_file_from_repo).parameters.keys() if key in kwargs
        }
        # Let's start by checking whether the processor class is saved in an image processor
        preprocessor_config_file = get_file_from_repo(
            pretrained_model_name_or_path, FEATURE_EXTRACTOR_NAME, **get_file_from_repo_kwargs
        )
        if preprocessor_config_file is not None:
            config_dict, _ = ImageProcessingMixin.get_image_processor_dict(pretrained_model_name_or_path, **kwargs)
            processor_class = config_dict.get("processor_class", None)
            if "AutoProcessor" in config_dict.get("auto_map", {}):
                processor_auto_map = config_dict["auto_map"]["AutoProcessor"]

        # If not found, let's check whether the processor class is saved in a feature extractor config
        if preprocessor_config_file is not None and processor_class is None:
            config_dict, _ = FeatureExtractionMixin.get_feature_extractor_dict(pretrained_model_name_or_path, **kwargs)
            processor_class = config_dict.get("processor_class", None)
            if "AutoProcessor" in config_dict.get("auto_map", {}):
                processor_auto_map = config_dict["auto_map"]["AutoProcessor"]

        if processor_class is None:
            # Next, let's check whether the processor class is saved in a tokenizer
            tokenizer_config_file = get_file_from_repo(
                pretrained_model_name_or_path, TOKENIZER_CONFIG_FILE, **get_file_from_repo_kwargs
            )
            if tokenizer_config_file is not None:
                with open(tokenizer_config_file, encoding="utf-8") as reader:
                    config_dict = json.load(reader)

                processor_class = config_dict.get("processor_class", None)
                if "AutoProcessor" in config_dict.get("auto_map", {}):
                    processor_auto_map = config_dict["auto_map"]["AutoProcessor"]

        if processor_class is None:
            # Otherwise, load config, if it can be loaded.
            if not isinstance(config, PretrainedConfig):
                config = AutoConfig.from_pretrained(
                    pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
                )

            # And check if the config contains the processor class.
            processor_class = getattr(config, "processor_class", None)
            if hasattr(config, "auto_map") and "AutoProcessor" in config.auto_map:
                processor_auto_map = config.auto_map["AutoProcessor"]

        if processor_class is not None:
            processor_class = processor_class_from_name(processor_class)

        has_remote_code = processor_auto_map is not None
        has_local_code = processor_class is not None or type(config) in PROCESSOR_MAPPING
        trust_remote_code = resolve_trust_remote_code(
            trust_remote_code, pretrained_model_name_or_path, has_local_code, has_remote_code
        )

        if has_remote_code and trust_remote_code:
            processor_class = get_class_from_dynamic_module(
                processor_auto_map, pretrained_model_name_or_path, **kwargs
            )
            _ = kwargs.pop("code_revision", None)
            if os.path.isdir(pretrained_model_name_or_path):
                processor_class.register_for_auto_class()
            return processor_class.from_pretrained(
                pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
            )
        elif processor_class is not None:
            return processor_class.from_pretrained(
                pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
            )
        # Last try: we use the PROCESSOR_MAPPING.
        elif type(config) in PROCESSOR_MAPPING:
            return PROCESSOR_MAPPING[type(config)].from_pretrained(pretrained_model_name_or_path, **kwargs)

        # At this stage, there doesn't seem to be a `Processor` class available for this model, so let's try a
        # tokenizer.
        try:
            return AutoTokenizer.from_pretrained(
                pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
            )
        except Exception:
            try:
                return AutoImageProcessor.from_pretrained(
                    pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
                )
            except Exception:
                pass

            try:
                return AutoFeatureExtractor.from_pretrained(
                    pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
                )
            except Exception:
                pass

        raise ValueError(
            f"Unrecognized processing class in {pretrained_model_name_or_path}. Can't instantiate a processor, a "
            "tokenizer, an image processor or a feature extractor for this model. Make sure the repository contains"
            "the files of at least one of those processing classes."
        )

    @staticmethod
    def register(config_class, processor_class, exist_ok=False):
        """
        Register a new processor for this class.

        Args:
            config_class ([`PretrainedConfig`]):
                The configuration corresponding to the model to register.
            processor_class ([`FeatureExtractorMixin`]): The processor to register.
        """
        PROCESSOR_MAPPING.register(config_class, processor_class, exist_ok=exist_ok)