\jlJ d Z ddlZddlZddlmZ ddlmZ ddlmZm Z ddl
m Z ddl m
Z
mZmZmZmZmZ d d
lmZ d d lmZ d d lmZmZmZmZ ej e Z eg d
Z ej e eee Z!de"fdZ# d de"ej$ z de"ej$ z dz de%de&e"e"f dz de%e"z dz de"dz de%fdZ' G d d Z(ddgZ)dS ) zAutoFeatureExtractor class. N) OrderedDict )PreTrainedConfig) get_class_from_dynamic_moduleresolve_trust_remote_code)FeatureExtractionMixin) CONFIG_NAMEFEATURE_EXTRACTOR_NAMEPROCESSOR_NAME cached_fileloggingsafe_load_json_file )_LazyAutoMapping) FEATURE_EXTRACTOR_MAPPING_NAMES)CONFIG_MAPPING_NAMES
AutoConfigmodel_type_to_module_name!replace_list_option_in_docstrings)#)audioflamingo3WhisperFeatureExtractor)csmEncodecFeatureExtractor)zdata2vec-audioWav2Vec2FeatureExtractor)glmasrr )granite_speech_plus GraniteSpeechFeatureExtractor)higgs_audio_v2_tokenizerDacFeatureExtractor)hubertr )inkling_mm_modelInklingFeatureExtractor)lasr_ctcLasrFeatureExtractor) lasr_encoderr$ )mimir ) moonshiner )moshir )musicgenr )nemotron3_5_asr$NemotronAsrStreamingFeatureExtractor) nemotron_asr_streaming_encoderr+ ) parakeet_ctcParakeetFeatureExtractor)parakeet_encoderr. )
parakeet_rnntr. ) parakeet_tdtr. )pe_audio_videoPeAudioFeatureExtractor) qwen2_5_omnir ) qwen2_audior )qwen3_omni_moer )seamless_m4t_v2SeamlessM4TFeatureExtractor)sewr )zsew-dr ) unispeechr )z
unispeech-satr )
vibevoice_asr*VibeVoiceAcousticTokenizerFeatureExtractor)voxtralr )z
wav2vec2-bertr )zwav2vec2-conformerr )wavlmr )xcodecr
class_namec t j D ]S\ }}| |v rJt | }t j d| d } t || c S # t $ r Y Ow xY wTt j D ]}t |dd | k r|c S t j d }t || rt || S d S )N.ztransformers.models__name__ transformers) r itemsr importlib
import_modulegetattrAttributeErrorFEATURE_EXTRACTOR_MAPPING_extra_contentvalueshasattr)r@ module_name
extractorsmodule extractor main_modules ^C:\Projects\DSCons\.venv\Lib\site-packages\transformers\models\auto\feature_extraction_auto.py!feature_extractor_class_from_namerT Q s #B#H#J#J Z # #3K@@K ,->->->@UVVF
vz22222!
$ /=DDFF 9j$ / /: = = >
).99K{J'' 0{J/// 4s A
A$#A$F pretrained_model_name_or_path cache_dirforce_downloadproxiestokenrevisionlocal_files_onlyc & t | t ||||||dd
}t | t ||||||dd
} | s |s t d i S d}
|t | } d| v r| d }
| |
t | }
|
pi S )a
Loads the feature extractor configuration from a pretrained model feature extractor 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
[`~FeatureExtractionMixin.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.
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 feature extractor configuration from local files.
Passing `token=True` is required when you want to use a private model.
Returns:
`Dict`: The configuration of the feature extractor.
Examples:
```python
# Download configuration from huggingface.co and cache.
feature_extractor_config = get_feature_extractor_config("facebook/wav2vec2-base-960h")
# This model does not have a feature extractor config so the result will be an empty dict.
feature_extractor_config = get_feature_extractor_config("FacebookAI/xlm-roberta-base")
# Save a pretrained feature extractor locally and you can reload its config
from transformers import AutoFeatureExtractor
feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/wav2vec2-base-960h")
feature_extractor.save_pretrained("feature-extractor-test")
feature_extractor_config = get_feature_extractor_config("feature-extractor-test")
```F) filenamerV rW rX rY rZ r[ _raise_exceptions_for_gated_repo%_raise_exceptions_for_missing_entriesz:Could not locate the feature extractor configuration file.Nfeature_extractor)r r r
loggerinfor ) rU rV rW rX rY rZ r[ kwargsresolved_processor_file resolved_feature_extractor_filefeature_extractor_dictprocessor_dicts rS get_feature_extractor_configrh i s D *% %))..3 '2%'%))..3 ' ' '# + 3J PQQQ
" *,-DEE . 0 0%34G%H "&27M7U!45T!U!U ! 'R' c h e Zd ZdZd Ze ee d Ze dd Z
dS )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.)OSError)selfs rS __init__z AutoFeatureExtractor.__init__ s
f
ri c | dd }| dd }d|d< t j |fi |\ }}| dd }d}d| di v r|d d }|b|`t |t
st
j |fd|i|}t |dd }t |d rd|j
v r
|j
d }|t | }|du} |dupt | t v }
|
o4|pt t | j d } | r5d
|v r | d
d } nd} t# |||
| | }| rJ|rH| sFt% ||fi |}| d d }| |j |fi |S | |j |fi |S t | t v r(t t | } |j |fi |S t) d
| dt* dt, dt, dd d t0 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 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.
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/")
```configNtrust_remote_codeT
_from_autofeature_extractor_typerk auto_mapz
transformers.z--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 3 K | ]}|V d S )N ).0cs rS z7AutoFeatureExtractor.from_pretrained..b s" @l@lq@l@l@l@l@l@lri )popr get_feature_extractor_dictget
isinstancer r from_pretrainedrH rM ru rT typerJ
__module__
startswithsplitr r register_for_auto_class
ValueErrorr
r joinr )
clsrU rc rq rr config_dict_feature_extractor_classfeature_extractor_auto_maphas_remote_codehas_local_codeexplicit_local_code
upstream_repos
rS r z$AutoFeatureExtractor.from_pretrained sR L Hd++ "JJ':D A A #| /JKhsslrss Q"-//2JD"Q"Q %)" ![__Z%D%D D D)4Z)@AW)X & # */I/Q f&677
#31 EVZ` '.f6NPT&U&U #vz**
U/E /X/X-3_=S-T* " .&GH_&`&` #4D@0<iV Pi@i , 1 # N'@f 'N
ZZ0021 111 : @ @ F Fq I
$
9!#@.Racp! ! d 0 d9L d&C*,I' 'MS' ' #
?D11A # ; ; = = =:*:;Xcc\bcc c
$
0:*:;Xcc\bcc c
&\\ 6
6
6&?V &M #:*:;Xcc\bcc c
o1N
o
o3I
o
oOZ
o
o(3
o
o7;yy@l@lLk@l@l@l7l7l
o
o
ri Fc @ t | || 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)rJ register) config_classr r s rS r z AutoFeatureExtractor.registere s' "**<9P[c*dddddri N)F) rC r __qualname____doc__ro classmethodr r r staticmethodr rx ri rS rk rk s
&&'FGG|
|
HG [|
| e e e \ e e eri rk rJ )NFNNNF)*r rF os collectionsr configuration_utilsr dynamic_module_utilsr r feature_extraction_utilsr utilsr r
r r r
r auto_factoryr
auto_mappingsr configuration_autor r r r
get_loggerrC ra 'MISSING_FEATURE_EXTRACTOR_MAPPING_NAMESupdaterJ strrT PathLikebooldictrh rk __all__rx ri rS r sr " ! # # # # # # 4 3 3 3 3 3 \ \ \ \ \ \ \ \ > > > > > > s s s s s s s s s s s s s s s s * * * * * * : : : : : :
H % %*5+$ $ $&+ &+ 'P ' &'N O O O , ,-ACb c c # 4 +/ %) # "k( k(#k(R[ 4'k( k( #s(^d
" k(
#: k( Dj
k( k( k( k( k(\Xe Xe Xe Xe Xe Xe Xe Xev '(>
?ri