
    sgL                        d Z ddlZddlZddlZddlZddlmZ ddlmZm	Z	m
Z
 ddlmZ ddlmZmZ ddlmZ dd	lmZmZmZmZ d
dlmZ d
dlmZmZmZmZ  ej<                  e      Z  eg d      Z! eee!      Z"de#fdZ$	 	 	 	 	 	 	 dde
e#ejJ                  f   de	e
e#ejJ                  f      de&de	e&   de	ee#e#f      de	e
e&e#f      de	e#   de&fdZ' G d d      Z(y)zAutoFeatureExtractor class.    N)OrderedDict)DictOptionalUnion   )PretrainedConfig)get_class_from_dynamic_moduleresolve_trust_remote_code)FeatureExtractionMixin)CONFIG_NAMEFEATURE_EXTRACTOR_NAMEget_file_from_repologging   )_LazyAutoMapping)CONFIG_MAPPING_NAMES
AutoConfigmodel_type_to_module_name!replace_list_option_in_docstrings)G)zaudio-spectrogram-transformerASTFeatureExtractor)beitBeitFeatureExtractor)chinese_clipChineseCLIPFeatureExtractor)clapClapFeatureExtractor)clipCLIPFeatureExtractor)clipsegViTFeatureExtractor)clvpClvpFeatureExtractor)conditional_detrConditionalDetrFeatureExtractor)convnextConvNextFeatureExtractor)cvtr&   )dacDacFeatureExtractor)zdata2vec-audioWav2Vec2FeatureExtractor)zdata2vec-visionr   )deformable_detrDeformableDetrFeatureExtractor)deitDeiTFeatureExtractor)detrDetrFeatureExtractor)dinatr    )z
donut-swinDonutFeatureExtractor)dptDPTFeatureExtractor)encodecEncodecFeatureExtractor)flavaFlavaFeatureExtractor)glpnGLPNFeatureExtractor)groupvitr   )hubertr*   )imagegptImageGPTFeatureExtractor)
layoutlmv2LayoutLMv2FeatureExtractor)
layoutlmv3LayoutLMv3FeatureExtractor)levitLevitFeatureExtractor)
maskformerMaskFormerFeatureExtractor)mctctMCTCTFeatureExtractor)mimir6   )mobilenet_v1MobileNetV1FeatureExtractor)mobilenet_v2MobileNetV2FeatureExtractor)	mobilevitMobileViTFeatureExtractor)moshir6   )natr    )owlvitOwlViTFeatureExtractor)	perceiverPerceiverFeatureExtractor)
poolformerPoolFormerFeatureExtractor)	pop2pianoPop2PianoFeatureExtractor)regnetr&   )resnetr&   )seamless_m4tSeamlessM4TFeatureExtractor)seamless_m4t_v2r]   )	segformerSegformerFeatureExtractor)sewr*   )zsew-dr*   )speech_to_textSpeech2TextFeatureExtractor)speecht5SpeechT5FeatureExtractor)swiftformerr    )swinr    )swinv2r    )ztable-transformerr0   )timesformerVideoMAEFeatureExtractor)tvltTvltFeatureExtractor)	unispeechr*   )zunispeech-satr*   )univnetUnivNetFeatureExtractor)vanr&   )videomaerj   )viltViltFeatureExtractor)vitr    )vit_maer    )vit_msnr    )wav2vec2r*   )zwav2vec2-bertr*   )zwav2vec2-conformerr*   )wavlmr*   )whisperWhisperFeatureExtractor)xclipr   )yolosYolosFeatureExtractor
class_namec                    t         j                         D ]<  \  }}| |v st        |      }t        j                  d| d      }	 t        ||       c S  t        j                  j                         D ]  \  }}t        |dd       | k(  s|c S  t        j                  d      }t        ||       rt        ||       S y # t        $ r Y w xY w)N.ztransformers.models__name__transformers)
FEATURE_EXTRACTOR_MAPPING_NAMESitemsr   	importlibimport_modulegetattrAttributeErrorFEATURE_EXTRACTOR_MAPPING_extra_contenthasattr)r~   module_name
extractorsmodule_	extractormain_modules          c/var/www/html/venv/lib/python3.12/site-packages/transformers/models/auto/feature_extraction_auto.py!feature_extractor_class_from_namer   w   s    #B#H#H#J Z#3K@K,,q->@UVFvz22 2@@FFH 99j$/:= )).9K{J'{J// " s   B<<	CCpretrained_model_name_or_path	cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_onlyc                 N   |j                  dd      }	|	)t        j                  dt               |t	        d      |	}t        | t        |||||||	      }
|
t        j                  d       i S t        |
d      5 }t        j                  |      cddd       S # 1 sw Y   yxY w)	a2  
    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 `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.
        local_files_only (`bool`, *optional*, defaults to `False`):
            If `True`, will only try to load the tokenizer configuration from local files.

    <Tip>

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

    </Tip>

    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`.)r   r   r   r   r   r   r   zdCould not locate the feature extractor configuration file, will try to use the model config instead.zutf-8)encoding)popwarningswarnFutureWarning
ValueErrorr   r   loggerinfoopenjsonload)r   r   r   r   r   r   r   r   kwargsr   resolved_config_filereaders               r   get_feature_extractor_configr      s    J ZZ 0$7N! A	
 uvv-%%')
 #r	
 		"W	5 !yy ! ! !s   <BB$c                   N    e Zd ZdZd Ze ee      d               Ze	dd       Z
y)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                     t        d      )NzAutoFeatureExtractor is designed to be instantiated using the `AutoFeatureExtractor.from_pretrained(pretrained_model_name_or_path)` method.)EnvironmentError)selfs    r   __init__zAutoFeatureExtractor.__init__   s    f
 	
    c                    |j                  dd      }|<t        j                  dt               |j	                  dd      t        d      ||d<   |j                  dd      }|j                  dd      }d|d	<   t        j                  |fi |\  }}|j	                  d
d      }d}	d|j	                  di       v r|d   d   }	|`|	^t        |t              st        j                  |fd|i|}t        |d
d      }t        |d      rd|j                  v r|j                  d   }	|t        |      }|	du}
|duxs t!        |      t"        v }t%        ||||
      }|
rc|rat'        |	|fi |}|j                  dd      }t(        j*                  j-                  |      r|j/                           |j0                  |fi |S | |j0                  |fi |S t!        |      t"        v r%t"        t!        |         } |j0                  |fi |S t        d| dt2         dt4         dt4         ddj7                  d t8        j;                         D               
      )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 `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 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   configtrust_remote_codeT
_from_autofeature_extractor_typer   auto_map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              3       K   | ]  }|  y w)N ).0cs     r   	<genexpr>z7AutoFeatureExtractor.from_pretrained.<locals>.<genexpr>  s     @sq@ss   )r   r   r   r   getr   r   get_feature_extractor_dict
isinstancer   r   from_pretrainedr   r   r   r   typer   r
   r	   ospathisdirregister_for_auto_class	from_dictr   r   joinr   keys)clsr   r   r   r   r   config_dictr   feature_extractor_classfeature_extractor_auto_maphas_remote_codehas_local_codes               r   r   z$AutoFeatureExtractor.from_pretrained  s   R  $4d;%MM E zz'4(4 l  -F7OHd+"JJ':DA#|/JJKhslrsQ"-//2JD"Q%)"![__Z%DD)4Z)@AW)X& #*/I/Qf&67#331EVZ` '.f6NPT&U#vz*/E/X-3__=S-T*".&GH_&`#4D@0<iVPi@i5<no
 0&C*,I'MS'# 

?D1Aww}}:;'??A4*44[KFKK$04*44[KFKK&\66&?V&M#4*44[KFKK01N0O P33I2J${m \((3}Btyy@sLkLpLpLr@s7s6tv
 	
r   c                 4    t         j                  | ||       y)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   s      r   r   zAutoFeatureExtractor.register  s     	"**<9P[c*dr   N)F)r   
__module____qualname____doc__r   classmethodr   r   r   staticmethodr   r   r   r   r   r      sH    
 &'FGD
 H D
L 	e 	er   r   )NFNNNNF))r   r   r   r   r   collectionsr   typingr   r   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   PathLikeboolr   r   r   r   r   <module>r      sE   "   	  # ( ( 4 \ > U U *  
		H	%"-HJ# X --ACbc # 4 48 &*(,(,""a!#(bkk)9#:a!c2;;./0a! a! d^	a!
 d38n%a! E$)$%a! sma! a!H`e `er   