Z jI S r SSKrSSKJrJr SSKJrJr SSK J
r
J r J r J
r
Jr \
R " \5 r " S S\5 rg) zZ
Sequence feature extraction class for common feature extractors to preprocess sequences.
N )is_valid_audio
load_audio) BatchFeatureFeatureExtractionMixin)PaddingStrategy
TensorTypeis_torch_tensorloggingto_numpyc ^ \ rS rSrSrS\S\S\4U 4S jjr SS\\ \ - \
\ \4 - \
\ \ \ 4 - \ \
\ \4 - S \ \ - \
- S
\S- S \ S \S- S
\ S- S\ \- S- S\4S jjrS\
R SS4S\
\ \R$ 4 \- S
\S- S\
S \S- S
\ S- S\
4 S jjr SS\
\ \R$ 4 \- S
\S- S \S- S \ S- 4S jjrSS jrS\ \ \ - \ \ \ - 4S jrSrU =r$ )SequenceFeatureExtractor a}
This is a general feature extraction class for speech recognition.
Args:
feature_size (`int`):
The feature dimension of the extracted features.
sampling_rate (`int`):
The sampling rate at which the audio files should be digitalized expressed in hertz (Hz).
padding_value (`float`):
The value that is used to fill the padding values / vectors.
feature_size
sampling_rate
padding_valuec > Xl X l X0l UR SS5 U l UR SS5 U l [ TU ] " S0 UD6 g )N padding_siderightreturn_attention_maskT )r r r popr r super__init__)selfr r r kwargs __class__s /root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/feature_extraction_sequence_utils.pyr !SequenceFeatureExtractor.__init__) sL ( * * "JJ~w ?%+ZZ0G%N"
"6" Nprocessed_featurespadding
max_length
truncationpad_to_multiple_ofr return_tensorsreturnc
^ ^ [ U[ [ 45 ( aV [ US [ [ 45 ( a8 US R 5 VV s0 s H oU V s/ s H oU PM sn _M nnn T R S U; a5 [ ST R S S[ UR 5 5 35 eUT R S n
Ub UO T R n[ U
5 S:X a U( a / US' U$ U
S n [ U [ [ 45 ( aA Sn [ X 5 S:X a U S-
n [ X 5 S:X a M U [ U
5 : a X S n Uce [ U 5 ( a SnOR[ U [ [ [ [ [ R 45 ( a SnO[ SU S [ U 5 S
35 eUR! 5 HP u p[ U
S [ [ 45 ( a [# U
5 X' M2 U
Vs/ s H n[# U5 PM snX' MR T R% X#S 9nUT R S n
[ U
5 m[' U4S jUR) 5 5 5 ( d [ S
5 e/ n[+ T5 HO nUR! 5 VVs0 s H u nnUUU _M nnnT R- UUUUS9nUR/ U5 MQ U[0 R2 :X a% [5 U 4S jU 5 5 n[0 R6 n0 n[+ T5 H nT R9 UU UUUUS9nUR! 5 Ht u pUU; a / UU' U
R: [ R: " [ R< 5 L a U
R? [ R@ 5 n
UU R/ U
5 Mv M [ UUS9$ s sn f s sn nf s snf s snnf )a
Pad input values / input vectors or a batch of input values / input vectors up to predefined length or to the
max sequence length in the batch.
Padding side (left/right) padding values are defined at the feature extractor level (with `self.padding_side`,
`self.padding_value`)
If the `processed_features` passed are dictionary of numpy arrays or PyTorch tensors the
result will use the same type unless you provide a different tensor type with `return_tensors`. In the case of
PyTorch tensors, you will lose the specific device of your tensors however.
Args:
processed_features ([`BatchFeature`], list of [`BatchFeature`], `dict[str, list[float]]`, `dict[str, list[list[float]]` or `list[dict[str, list[float]]]`):
Processed inputs. Can represent one input ([`BatchFeature`] or `dict[str, list[float]]`) or a batch of
input values / vectors (list of [`BatchFeature`], *dict[str, list[list[float]]]* or *list[dict[str,
list[float]]]*) so you can use this method during preprocessing as well as in a PyTorch Dataloader
collate function.
Instead of `list[float]` you can have tensors (numpy arrays or PyTorch tensors),
see the note above for the return type.
padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`):
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)
return_tensors (`str` or [`~utils.TensorType`], *optional*):
If set, will return tensors instead of list of python integers. Acceptable values are:
- `'pt'`: Return PyTorch `torch.Tensor` objects.
- `'np'`: Return Numpy `np.ndarray` objects.
r zYou should supply an instance of `transformers.BatchFeature` or list of `transformers.BatchFeature` to this method that includes z, but you provided attention_maskr ptnpztype of z
unknown: z6. Should be one of a python, numpy, or pytorch object.)r" r# c 3 @ ># U H n[ U5 T:H v M g 7f)N)len).0v
batch_sizes r /SequenceFeatureExtractor.pad.. s M1LA3q6Z'1Ls zLSome items in the output dictionary have a different batch size than others.)r# r% r$ c 3 Z ># U H n[ UTR S 5 v M" g7f)r N)r- model_input_names)r. input_slicer s r r1 r2 s+ m\l[ST-C-CA-F!G H H\ls (+)r# padding_strategyr% r ) tensor_type)!
isinstancelisttupledictr keysr4
ValueErrorr r- r
intfloatr+ ndarraytypeitemsr _get_padding_strategiesallvaluesrange _truncateappendr LONGESTmax
MAX_LENGTH_paddtypefloat64astypefloat32)r r! r" r# r$ r% r r& keyexamplerequired_input
first_elementindexvaluer/ r6 truncated_inputsikinputs inputs_slice
batch_outputsoutputsr0 s ` @r pad SequenceFeatureExtractor.pad3 s L (4- 8 8ZHZ[\H]`dfr_s=t=t RddeQfQkQkQm"Qm#2DE2Dwcl2DEEQm
"
! !! $,> > 1151G1G1J0K L+002346
,D,B,B1,EF%:%F !DLfLf ~ ! #$79"#34% % 'q)
mdE] 3 3En+,1
n+,1s>** . 5a 8
! }--!%MCeRZZ+PQQ!% }oZ]8K7L MK K
-224JC%(S%L11*25/"'@E*F18A;*F"' 5 777_+D,B,B1,EF (
M1C1J1J1LMMM kl l z"A*<*B*B*DE*D$!Qa1g*DFE >>%#5% * L
# #L 1 # 6 6 6 m\l mmJ . 9 9
z"Aii #%!1#5&; G &mmo
m+)+M#&;;"((2::"66 !LL 4E c"))%0 . #" M~FF F"d +G Fs$
O" O *O" O(+O- O"r6 c XR S nU[ R :X a [ U5 nUb Ub X$- S:w a
X$- S- U- nU[ R :g =( a [ U5 U: nU( a5 SU; a/ [
R " [ U5 [
R S9US' U( Ga1 U[ U5 -
nU R S:X aq U( a [
R " US SU45 US' U R S: a SU4S4OSU4n [
R " XiSU R S9XR S ' U$ U R S :X aq U( a [
R " US US45 US' U R S: a US4S4OUS4n [
R " XiSU R S9XR S ' U$ [ S
[ U R 5 - 5 eU$ ) a
Pad inputs (on left/right and up to predefined length or max length in the batch)
Args:
processed_features (`Union[dict[str, np.ndarray], BatchFeature]`):
Dictionary of input values (`np.ndarray[float]`) / input vectors (`list[np.ndarray[float]]`) or batch
of inputs values (`list[np.ndarray[int]]`) / input vectors (`list[np.ndarray[int]]`)
max_length (`int`, *optional*):
Maximum length of the returned list and optionally padding length (see below)
padding_strategy (`PaddingStrategy`, *optional*, default to `PaddingStrategy.DO_NOT_PAD`):
PaddingStrategy to use for padding.
- PaddingStrategy.LONGEST Pad to the longest sequence in the batch
- PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
- PaddingStrategy.DO_NOT_PAD: Do not pad
The feature_extractor padding sides are defined in self.padding_side:
- 'left': pads on the left of the sequences
- 'right': pads on the right of the sequences
pad_to_multiple_of (`int`, *optional*):
Integer if set will pad the sequence to a multiple of the provided value. This is especially useful to
enable the use of Tensor Core 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*):
Set to False to avoid returning attention mask (default: set to model specifics)
r r r) )rM r )r r constant)constant_valuesleftzInvalid padding strategy:)r4 r rI r-
DO_NOT_PADr+ onesint32r r^ r r r= str)
r r! r# r6 r% r rS needs_to_be_padded
difference
padding_shapes
r rL SequenceFeatureExtractor._pad s D ,,B,B1,EF 6 6 6 ^,J !&8&D*JimnJn%;q@DVVJ - 1K1K K pPSTbPcfpPp %5=O%O35773~;NVXV^V^3_ / 0 #c.&99J G+(;=66*+;B=N=NQR=R!Z & 9YZ\fXg
@B":tOaOaA"#9#9!#<= "! ""f,(;=66*+;B=N=NQR=R*a & 9YcefXg
@B":tOaOaA"#9#9!#<= "! !!= 7.5` (Volta), or on TPUs
which benefit from having sequence lengths be a multiple of 128.
truncation (`bool`, *optional*):
Activates truncation to cut input sequences longer than `max_length` to `max_length`.
NzKWhen setting ``truncation=True``, make sure that ``max_length`` is defined.r r r) )r= r4 r- )r r! r# r% r$ rS needs_to_be_truncateds r rG "SequenceFeatureExtractor._truncate% s . % %
J . jk k+,B,B1,EF !&8&D*JimnJn%;q@DVVJ #N 3j @ r? r r r9 r; rg boolr r r^ rd r+ r@ rL rG rC rs __static_attributes__
__classcell__)r s @r r r s
#S # #U #" 15!% )--126hG (
|
sL
! " sD &&
' ( tC %&
' (hG o-hG $JhG hG $JhG $d{hG j(4/hG
hGZ "&,;,F,F)--1
F" bjj 1L @F" $JF" * F"
$J F" $d{
F"
F"V "&)-"& )" bjj 1L @)" $J)" $J )"
4K )"V @wS49_tDI-N w wr r )r{ numpyr+ audio_utilsr r feature_extraction_utilsr r utilsr r r
r r
get_loggerrw loggerr r r r r s> 3 J R R
H %bw 5 bwr