cCiY- S r SSKJrJr SSKrSSKJr SSKJ r SSK
J r J r J
r
\
R " \5 r " S S \5 rS /rg)
z&
Feature extractor class for Wav2Vec2
)OptionalUnionN )SequenceFeatureExtractor) BatchFeature)PaddingStrategy
TensorTypeloggingc | ^ \ rS rSrSrSS/r SU 4S jjr\ SS\\ R S\\ R S\ S\\ R 4S jj5 r SS \
\ R \\ \\ R \\\ 4 S
\
\\\4 S \\ S \S
\\ S\\ S\\
\\4 S\\ S\4S jjrSrU =r$ )Wav2Vec2FeatureExtractor a
Constructs a Wav2Vec2 feature extractor.
This feature extractor inherits from [`~feature_extraction_sequence_utils.SequenceFeatureExtractor`] which contains
most of the main methods. Users should refer to this superclass for more information regarding those methods.
Args:
feature_size (`int`, *optional*, defaults to 1):
The feature dimension of the extracted features.
sampling_rate (`int`, *optional*, defaults to 16000):
The sampling rate at which the audio files should be digitalized expressed in hertz (Hz).
padding_value (`float`, *optional*, defaults to 0.0):
The value that is used to fill the padding values.
do_normalize (`bool`, *optional*, defaults to `True`):
Whether or not to zero-mean unit-variance normalize the input. Normalizing can help to significantly
improve the performance for some models, *e.g.*,
[wav2vec2-lv60](https://huggingface.co/models?search=lv60).
return_attention_mask (`bool`, *optional*, defaults to `False`):
Whether or not [`~Wav2Vec2FeatureExtractor.__call__`] should return `attention_mask`.
Wav2Vec2 models that have set `config.feat_extract_norm == "group"`, such as
[wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base-960h), have **not** been trained using
`attention_mask`. For such models, `input_values` should simply be padded with 0 and no `attention_mask`
should be passed.
For Wav2Vec2 models that have set `config.feat_extract_norm == "layer"`, such as
[wav2vec2-lv60](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self), `attention_mask` should be
passed for batched inference.
input_valuesattention_maskc D > [ TU ] " SXUS.UD6 X@l XPl g )N) feature_size
sampling_rate
padding_value )super__init__return_attention_mask do_normalize)selfr r r r r kwargs __class__s r/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/wav2vec2/feature_extraction_wav2vec2.pyr !Wav2Vec2FeatureExtractor.__init__C s* wl_lwpvw%:" ( r returnc Ub [ R " U[ R 5 n/ n[ XR S5 5 Hl u pEXDSU R 5 -
[ R " USU R 5 S- 5 - nXVR S : a X&US& UR U5 Mn U$ U Vs/ s H= owUR 5 -
[ R " UR 5 S- 5 - PM? nnU$ s snf )zK
Every array in the list is normalized to have zero mean and unit variance
NgHz>r )
nparrayint32zipsummeansqrtvarshapeappend)r r r normed_input_valuesvectorlength normed_slicexs r zero_mean_unit_var_norm0Wav2Vec2FeatureExtractor.zero_mean_unit_var_normP s % XXnbhh ?N"$ "%l4F4Fr4J"K & )=)=)? ?2776RYSY?K^K^K`cgKgCh h . .q 11,9)#**<8 #L #" Vb"bUaPQLBGGAEEGdN4K#KUa "b"" #cs ;AD
raw_speechpadding
max_length
truncationpad_to_multiple_ofr return_tensorsr c Ub< XR :w a, [ SU SU R SU R SU S3 5 eO-[ R SU R R
S35 [
U[ R 5 =( a [ UR 5 S : n
U
( a' [ UR 5 S
: a [ S U 35 eU
=( dE [
U[ [ 45 =( a( [
US [ R [ [ 45 n U ( d U/n[ S
U05 n U R U UUUUUS9n
U
S
n[
US [ R 5 ( d9 U Vs/ s H& n[ R " U[ R S9PM( snU
S
' GO[
U[ R 5 ( d [
US [ R 5 ( ag US R" [ R" " [ R$ 5 L a3 U Vs/ s H! oR' [ R 5 PM# snU
S
' Or[
U[ R 5 ( aS UR" [ R" " [ R$ 5 L a" UR' [ R 5 U
S
' U
R) S5 nUb7 U Vs/ s H& n[ R " U[ R* S9PM( snU
S' U R, ( aE U R/ X#S9[0 R2 La UOSnU R5 U
S
UU R6 S9U
S
' Ub U
R9 U5 n
U
$ s snf s snf s snf )ap
Main method to featurize and prepare for the model one or several sequence(s).
Args:
raw_speech (`np.ndarray`, `list[float]`, `list[np.ndarray]`, `list[list[float]]`):
The sequence or batch of sequences to be padded. Each sequence can be a numpy array, a list of float
values, a list of numpy arrays or a list of list of float values. Must be mono channel audio, not
stereo, i.e. single float per timestep.
padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
Select a strategy to pad the returned sequences (according to the model's padding side and padding
index) among:
- `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
sequence if provided).
- `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
acceptable input length for the model if that argument is not provided.
- `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
lengths).
max_length (`int`, *optional*):
Maximum length of the returned list and optionally padding length (see above).
truncation (`bool`):
Activates truncation to cut input sequences longer than *max_length* to *max_length*.
pad_to_multiple_of (`int`, *optional*):
If set will pad the sequence to a multiple of the provided value.
This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability
`>= 7.5` (Volta), or on TPUs which benefit from having sequence lengths be a multiple of 128.
return_attention_mask (`bool`, *optional*):
Whether to return the attention mask. If left to the default, will return the attention mask according
to the specific feature_extractor's default.
[What are attention masks?](../glossary#attention-mask)
Wav2Vec2 models that have set `config.feat_extract_norm == "group"`, such as
[wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base-960h), have **not** been trained using
`attention_mask`. For such models, `input_values` should simply be padded with 0 and no
`attention_mask` should be passed.
For Wav2Vec2 models that have set `config.feat_extract_norm == "layer"`, such as
[wav2vec2-lv60](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self), `attention_mask` should
be passed for batched inference.
return_tensors (`str` or [`~utils.TensorType`], *optional*):
If set, will return tensors instead of list of python integers. Acceptable values are:
- `'tf'`: Return TensorFlow `tf.constant` objects.
- `'pt'`: Return PyTorch `torch.Tensor` objects.
- `'np'`: Return Numpy `np.ndarray` objects.
sampling_rate (`int`, *optional*):
The sampling rate at which the `raw_speech` input was sampled. It is strongly recommended to pass
`sampling_rate` at the forward call to prevent silent errors.
padding_value (`float`, *optional*, defaults to 0.0):
Nz3The model corresponding to this feature extractor: z& was trained using a sampling rate of zI. Please make sure that the provided `raw_speech` input was sampled with z and not .zDIt is strongly recommended to pass the `sampling_rate` argument to `zN()`. Failing to do so can result in silent errors that might be hard to debug. z2Only mono-channel audio is supported for input to r r )r4 r5 r6 r7 r )dtyper )r5 )r r ) r
ValueErrorloggerwarningr __name__
isinstancer" ndarraylenr* listtupler padasarrayfloat32r= float64astypegetr$ r _get_padding_strategiesr
DO_NOT_PADr1 r convert_to_tensors)r r3 r4 r5 r6 r7 r r8 r r is_batched_numpy
is_batchedencoded_inputs
padded_inputsr r# r s r __call__!Wav2Vec2FeatureExtractor.__call__f s; L $ 2 22 I$ P **+ , **+9]O1F 3
NNVW[WeWeWnWnVo p\ \
&j"**=[#jFVFVBWZ[B[ J$4$4 5 9 QRVQW XY Y%
zD%= 1 lz*Q-RTR\R\^ceiQj7k
$ J &~z&BC !! 1"7
!
%^4 ,q/2::66^j,k^jUZRZZRZZ-P^j,kM. )<44<?BJJ77 Q%%"**)==S_,`S_%\\"**-ES_,`M. )
bjj
1
1l6H6HBHHUWU_U_L`6`,8,?,?
,KM. ) '**+;< %^l.m^lUZrzz%rxx/P^l.mM* + ///OWfWqWqq
-1,H,H n-n\`\n\n -I -M. ) % ) < <^ LM ; -l -a /ns 8-M>&(N -N)r r )r; i> FT)rV )FNFNNNN)rA
__module__ __qualname____firstlineno____doc__model_input_namesr staticmethodrE r" rC floatr1 r boolstrr r intr r rT __static_attributes__
__classcell__)r s @r r r sU B ()9: #
) ad#2::rj sJ # I 4 9 9
H %Q 7 Q h &
&r