o
iP @ s^ d Z ddlZddlZddlZddlZddlmZ ddlmZm Z ddl
m Z ddl m
Z
mZ ddlmZ dd lmZmZmZmZ d
d lmZ d
d lmZmZmZm Z e e Z eg d
Z eee Z!de"fddZ# d de e"ej$f dee e"ej$f de%dee% dee&e"e"f dee e%e"f dee" de%fddZ'G d d d Z(d d gZ)dS ) zAutoFeatureExtractor class. N) OrderedDict)OptionalUnion )PretrainedConfig) get_class_from_dynamic_moduleresolve_trust_remote_code)FeatureExtractionMixin) CONFIG_NAMEFEATURE_EXTRACTOR_NAME cached_filelogging )_LazyAutoMapping)CONFIG_MAPPING_NAMES
AutoConfigmodel_type_to_module_name!replace_list_option_in_docstrings)P)z audio-spectrogram-transformerASTFeatureExtractor)beitBeitFeatureExtractor) chinese_clipChineseCLIPFeatureExtractor)clapClapFeatureExtractor)clipCLIPFeatureExtractor)clipsegViTFeatureExtractor)clvpClvpFeatureExtractor)conditional_detr ConditionalDetrFeatureExtractor)convnextConvNextFeatureExtractor)cvtr$ )dacDacFeatureExtractor)zdata2vec-audioWav2Vec2FeatureExtractor)zdata2vec-visionr )deformable_detr DeformableDetrFeatureExtractor)deitDeiTFeatureExtractor)detrDetrFeatureExtractor)diaDiaFeatureExtractor)dinatr )z
donut-swinDonutFeatureExtractor)dptDPTFeatureExtractor)encodecEncodecFeatureExtractor)flavaFlavaFeatureExtractor)gemma3n Gemma3nAudioFeatureExtractor)glpnGLPNFeatureExtractor)granite_speech GraniteSpeechFeatureExtractor)groupvitr )hubertr( )imagegptImageGPTFeatureExtractor)kyutai_speech_to_text"KyutaiSpeechToTextFeatureExtractor)
layoutlmv2LayoutLMv2FeatureExtractor)
layoutlmv3LayoutLMv3FeatureExtractor)levitLevitFeatureExtractor)
maskformerMaskFormerFeatureExtractor)mctctMCTCTFeatureExtractor)mimir6 ) mobilenet_v1MobileNetV1FeatureExtractor) mobilenet_v2MobileNetV2FeatureExtractor) mobilevitMobileViTFeatureExtractor) moonshiner( )moshir6 )natr )owlvitOwlViTFeatureExtractor) parakeet_ctcParakeetFeatureExtractor)parakeet_encoderr\ ) perceiverPerceiverFeatureExtractor)phi4_multimodal Phi4MultimodalFeatureExtractor)
poolformerPoolFormerFeatureExtractor) pop2pianoPop2PianoFeatureExtractor)regnetr$ )resnetr$ ) seamless_m4tSeamlessM4TFeatureExtractor)seamless_m4t_v2ri ) segformerSegformerFeatureExtractor)sewr( )zsew-dr( )speech_to_textSpeech2TextFeatureExtractor)speecht5SpeechT5FeatureExtractor) swiftformerr )swinr )swinv2r )ztable-transformerr. ) timesformerVideoMAEFeatureExtractor)tvltTvltFeatureExtractor) unispeechr( )z
unispeech-satr( )univnetUnivNetFeatureExtractor)vanr$ )videomaerv )viltViltFeatureExtractor)vitr )vit_maer )vit_msnr )wav2vec2r( )z
wav2vec2-bertr( )zwav2vec2-conformerr( )wavlmr( )whisperWhisperFeatureExtractor)xclipr )xcodecr' )yolosYolosFeatureExtractor
class_namec C s t D ]'\}}| |v r+t|}td| d}zt|| W S ty* Y qw qtj D ]}t|dd | kr?| S q1td}t
|| rOt|| S d S )N.ztransformers.models__name__ transformers) FEATURE_EXTRACTOR_MAPPING_NAMESitemsr importlib
import_modulegetattrAttributeErrorFEATURE_EXTRACTOR_MAPPING_extra_contentvalueshasattr)r module_name
extractorsmodule extractor main_module r d/home/ubuntu/.local/lib/python3.10/site-packages/transformers/models/auto/feature_extraction_auto.py!feature_extractor_class_from_name s$
r F pretrained_model_name_or_path cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_onlyc K s | dd} | durtdt |durtd| }t| t|||||||dddd }
|
du r5td i S t |
dd
} t
| W d S 1 sKw Y dS )
a*
Loads the tokenizer configuration from a pretrained model tokenizer configuration.
Args:
pretrained_model_name_or_path (`str` or `os.PathLike`):
This can be either:
- a string, the *model id* of a pretrained model configuration hosted inside a model repo on
huggingface.co.
- a path to a *directory* containing a configuration file saved using the
[`~PreTrainedTokenizer.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 configuration 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 configuration files and override the cached versions if they
exist.
resume_download:
Deprecated and ignored. All downloads are now resumed by default when possible.
Will be removed in v5 of Transformers.
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 `hf auth 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.
local_files_only (`bool`, *optional*, defaults to `False`):
If `True`, will only try to load the tokenizer configuration from local files.
Passing `token=True` is required when you want to use a private model.
Returns:
`Dict`: The configuration of the tokenizer.
Examples:
```python
# Download configuration from huggingface.co and cache.
tokenizer_config = get_tokenizer_config("google-bert/bert-base-uncased")
# This model does not have a tokenizer config so the result will be an empty dict.
tokenizer_config = get_tokenizer_config("FacebookAI/xlm-roberta-base")
# Save a pretrained tokenizer locally and you can reload its config
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-cased")
tokenizer.save_pretrained("tokenizer-test")
tokenizer_config = get_tokenizer_config("tokenizer-test")
```use_auth_tokenNrThe `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.V`token` and `use_auth_token` are both specified. Please set only the argument `token`.F)
r r r r r r r _raise_exceptions_for_gated_repo%_raise_exceptions_for_missing_entries'_raise_exceptions_for_connection_errorszdCould not locate the feature extractor configuration file, will try to use the model config instead.zutf-8)encoding) popwarningswarn
FutureWarning
ValueErrorr r loggerinfoopenjsonload) r r r r r r r r kwargsr resolved_config_filereaderr r r get_feature_extractor_config s> E$r c @ s: e Zd ZdZdd Zeeedd Ze d
ddZ
d S ) AutoFeatureExtractora+
This is a generic feature extractor class that will be instantiated as one of the feature extractor classes of the
library when created with the [`AutoFeatureExtractor.from_pretrained`] class method.
This class cannot be instantiated directly using `__init__()` (throws an error).
c C s t d)NzAutoFeatureExtractor is designed to be instantiated using the `AutoFeatureExtractor.from_pretrained(pretrained_model_name_or_path)` method.)OSError)selfr r r __init__ s z AutoFeatureExtractor.__init__c
K s | dd}|dur tdt |ddurtd||d< | dd}| dd}d|d < tj|fi |\}}|d
d}d} d |d i v rP|d d } |du r}| du r}t|t sht
j |fd|i|}t |d
d}t
|d r}d |jv r}|jd } |durt|}| du}
|dupt|tv } |
rd
| v r| d
d } nd} t||| |
| }|
r|rt| |fi |}| dd}| |j|fi |S |dur|j|fi |S t|tv rtt| }|j|fi |S td| dt dt dt dddd tD
)a}
Instantiate one of the feature extractor classes of the library from a pretrained model vocabulary.
The feature extractor 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), or when it's
missing, by falling back to using pattern matching on `pretrained_model_name_or_path`:
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.
- 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:
Deprecated and ignored. All downloads are now resumed by default when possible.
Will be removed in v5 of Transformers.
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 `hf auth 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.
Passing `token=True` is required when you want to use a private model.
Examples:
```python
>>> from transformers import AutoFeatureExtractor
>>> # Download feature extractor from huggingface.co and cache.
>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/wav2vec2-base-960h")
>>> # If feature extractor files are in a directory (e.g. feature extractor was saved using *save_pretrained('./test/saved_model/')*)
>>> # feature_extractor = AutoFeatureExtractor.from_pretrained("./test/saved_model/")
```r Nr r r configtrust_remote_codeT
_from_autofeature_extractor_typer auto_mapz--r
code_revisionz"Unrecognized feature extractor in z4. Should have a `feature_extractor_type` key in its z of z3, or one of the following `model_type` keys in its z: z, c s s | ]}|V qd S )Nr ).0cr r r s z7AutoFeatureExtractor.from_pretrained..)r r r r getr r get_feature_extractor_dict
isinstancer r from_pretrainedr r r r typer splitr r register_for_auto_class from_dictr r
joinr )
clsr r r r r config_dict_feature_extractor_classfeature_extractor_auto_maphas_remote_codehas_local_code
upstream_repor r r r
s I
z$AutoFeatureExtractor.from_pretrainedFc C s t j| ||d dS )a0
Register a new feature extractor for this class.
Args:
config_class ([`PretrainedConfig`]):
The configuration corresponding to the model to register.
feature_extractor_class ([`FeatureExtractorMixin`]): The feature extractor to register.
)exist_okN)r register) config_classr r r r r r s
z AutoFeatureExtractor.registerN)F) r
__module__ __qualname____doc__r classmethodr r r staticmethodr r r r r r s r r )NFNNNNF)*r r r osr collectionsr typingr r configuration_utilsr dynamic_module_utilsr r feature_extraction_utilsr utilsr
r r r
auto_factoryr configuration_autor r r r
get_loggerr r r r strr PathLikebooldictr r __all__r r r r s\
U
g (