ZjZ+lSrSSKrSSKJr SSKJr SSKJr \"SS9\"S S \555rS /r g) zData2VecText configurationN)strict)PreTrainedConfig)auto_docstringz!facebook/data2vec-audio-base-960h) checkpointc^\rSrSr%SrSrSr\\S'Sr \\S'Sr \\S 'Sr \\S 'S r \\S 'S r \\S'Sr\\-\S'Sr\\-\S'Sr\\-\S'Sr\\-\S'Sr\\-\S'Sr\\-\S'Sr\\S'Sr\\S'S r\\S'Sr\\\\S4-\S'Sr\\\\S4-\S 'S!r\\\\S4-\S"'S#r\\S$'S%r \\S&'S'r!\\S('S)r"\\S*'S+r#\\-\S,'S-r$\\S.'S/r%\\S0'Sr&\\-\S1'S-r'\\S2'S3r(\\S4'S5r)\\S6'S#r*\\S7'S#r+\\S8'S9r,\\S:'S;r-\\\\S4-\S<'S=r.\\\\S4-\S>'S?r/\\\\S4-\S@'SAr0\\SB'S3r1\SC-\SD'SEr2\SC-\SF'S/r3\\\-SC-\SG'S#r4\\SH'SIr5\\SJ'S/r6\\SK'SIr7\\SL'SCr8\SC-\SM'U4SNjr9SOr:\;SP5r$)RData2VecAudioConfiga feat_proj_dropout (`float`, *optional*, defaults to 0.0): The dropout probability for output of the feature encoder. final_dropout (`float`, *optional*, defaults to 0.1): The dropout probability for the final projection layer of [`Data2VecAudioForCTC`]. feat_extract_activation (`str, `optional`, defaults to `"gelu"`): The non-linear activation function (function or string) in the 1D convolutional layers of the feature extractor. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. conv_dim (`tuple[int]` or `list[int]`, *optional*, defaults to `(512, 512, 512, 512, 512, 512, 512)`): A tuple of integers defining the number of input and output channels of each 1D convolutional layer in the feature encoder. The length of *conv_dim* defines the number of 1D convolutional layers. conv_stride (`tuple[int]` or `list[int]`, *optional*, defaults to `(5, 2, 2, 2, 2, 2, 2)`): A tuple of integers defining the stride of each 1D convolutional layer in the feature encoder. The length of *conv_stride* defines the number of convolutional layers and has to match the length of *conv_dim*. conv_bias (`bool`, *optional*, defaults to `False`): Whether the 1D convolutional layers have a bias. num_conv_pos_embedding_groups (`int`, *optional*, defaults to 16): Number of groups of 1D convolutional positional embeddings layer. conv_pos_kernel_size (`int`, *optional*, defaults to `19`): Kernel size of positional conv module. num_conv_pos_embeddings (`int`, *optional*, defaults to 128): Number of convolutional positional embeddings. Defines the kernel size of 1D convolutional positional embeddings layer. mask_time_prob (`float`, *optional*, defaults to 0.05): Percentage (between 0 and 1) of all feature vectors along the time axis which will be masked. The masking procedure generates ''mask_time_prob*len(time_axis)/mask_time_length'' independent masks over the axis. If reasoning from the probability of each feature vector to be chosen as the start of the vector span to be masked, *mask_time_prob* should be `prob_vector_start*mask_time_length`. Note that overlap may decrease the mask_time_length (`int`, *optional*, defaults to 10): Length of vector span along the time axis. mask_time_min_masks (`int`, *optional*, defaults to 2),: The minimum number of masks of length `mask_feature_length` generated along the time axis, each time step, irrespectively of `mask_feature_prob`. Only relevant if ''mask_time_prob*len(time_axis)/mask_time_length < mask_time_min_masks'' mask_feature_prob (`float`, *optional*, defaults to 0.0): Percentage (between 0 and 1) of all feature vectors along the feature axis which will be masked. The masking procedure generates ''mask_feature_prob*len(feature_axis)/mask_time_length'' independent masks over the axis. If reasoning from the probability of each feature vector to be chosen as the start of the vector span to be masked, *mask_feature_prob* should be `prob_vector_start*mask_feature_length`. Note that overlap may decrease the actual percentage of masked vectors. This is only relevant if `apply_spec_augment is True`. mask_feature_length (`int`, *optional*, defaults to 10): Length of vector span along the feature axis. mask_feature_min_masks (`int`, *optional*, defaults to 0): The minimum number of masks of length `mask_feature_length` generated along the feature axis, each time step, irrespectively of `mask_feature_prob`. Only relevant if ''mask_feature_prob*len(feature_axis)/mask_feature_length < mask_feature_min_masks'' ctc_loss_reduction (`str`, *optional*, defaults to `"sum"`): Specifies the reduction to apply to the output of `torch.nn.CTCLoss`. Only relevant when training an instance of [`Data2VecAudioForCTC`]. ctc_zero_infinity (`bool`, *optional*, defaults to `False`): Whether to zero infinite losses and the associated gradients of `torch.nn.CTCLoss`. Infinite losses mainly occur when the inputs are too short to be aligned to the targets. Only relevant when training an instance of [`Data2VecAudioForCTC`]. use_weighted_layer_sum (`bool`, *optional*, defaults to `False`): Whether to use a weighted average of layer outputs with learned weights. Only relevant when using an instance of [`Data2VecAudioForSequenceClassification`]. classifier_proj_size (`int`, *optional*, defaults to 256): Dimensionality of the projection before token mean-pooling for classification. tdnn_dim (`tuple[int]` or `list[int]`, *optional*, defaults to `(512, 512, 512, 512, 1500)`): A tuple of integers defining the number of output channels of each 1D convolutional layer in the *TDNN* module of the *XVector* model. The length of *tdnn_dim* defines the number of *TDNN* layers. tdnn_kernel (`tuple[int]` or `list[int]`, *optional*, defaults to `(5, 3, 3, 1, 1)`): A tuple of integers defining the kernel size of each 1D convolutional layer in the *TDNN* module of the *XVector* model. The length of *tdnn_kernel* has to match the length of *tdnn_dim*. tdnn_dilation (`tuple[int]` or `list[int]`, *optional*, defaults to `(1, 2, 3, 1, 1)`): A tuple of integers defining the dilation factor of each 1D convolutional layer in *TDNN* module of the *XVector* model. The length of *tdnn_dilation* has to match the length of *tdnn_dim*. xvector_output_dim (`int`, *optional*, defaults to 512): Dimensionality of the *XVector* embedding vectors. add_adapter (`bool`, *optional*, defaults to `False`): Whether a convolutional network should be stacked on top of the Data2VecAudio Encoder. Can be very useful for warm-starting Data2VecAudio for SpeechEncoderDecoder models. adapter_kernel_size (`int`, *optional*, defaults to 3): Kernel size of the convolutional layers in the adapter network. Only relevant if `add_adapter is True`. adapter_stride (`int`, *optional*, defaults to 2): Stride of the convolutional layers in the adapter network. Only relevant if `add_adapter is True`. num_adapter_layers (`int`, *optional*, defaults to 3): Number of convolutional layers that should be used in the adapter network. Only relevant if `add_adapter is True`. output_hidden_size (`int`, *optional*): Dimensionality of the encoder output layer. If not defined, this defaults to *hidden-size*. Only relevant if `add_adapter is True`. Example: ```python >>> from transformers import Data2VecAudioConfig, Data2VecAudioModel >>> # Initializing a Data2VecAudio facebook/data2vec-audio-base-960h style configuration >>> configuration = Data2VecAudioConfig() >>> # Initializing a model (with random weights) from the facebook/data2vec-audio-base-960h style configuration >>> model = Data2VecAudioModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```zdata2vec-audio vocab_sizei hidden_size num_hidden_layersnum_attention_headsi intermediate_sizegelu hidden_actg?hidden_dropoutactivation_dropoutattention_dropoutgfeat_proj_dropout final_dropout layerdropg{Gz?initializer_rangegh㈵>layer_norm_epsfeat_extract_activation)rrrrrr.conv_dim)r r r r r conv_stride) rrrrr r conv_kernelF conv_biasnum_conv_pos_embedding_groupsconv_pos_kernel_sizernum_conv_pos_embeddingsg?mask_time_probr"mask_time_lengthr mask_time_min_masksmask_feature_probmask_feature_lengthrmask_feature_min_maskssumctc_loss_reductionctc_zero_infinityuse_weighted_layer_sumclassifier_proj_size)rrrritdnn_dim)rrrr7 tdnn_kernel)r7r rr7r7 tdnn_dilationrxvector_output_dimN pad_token_idr7 bos_token_id eos_token_id add_adapterradapter_kernel_sizeadapter_stridenum_adapter_layersoutput_hidden_sizec >UR=(d URUl[UR5Ul[ TU]"S0UD6 g)N)rBr lenrnum_feat_extract_layerssuper __post_init__)selfkwargs __class__s ڊ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/data2vec/configuration_data2vec_audio.pyrH!Data2VecAudioConfig.__post_init__s="&"9"9"MT=M=M'*4=='9$ ''c r[UR5UR:wdF[UR5UR:wd#[UR5UR:waN[ S[UR5S[UR5S[UR5S35eg)zOPart of `@strict`-powered validation. Validates the architecture of the config.zConfiguration for convolutional layers is incorrect. It is required that `len(config.conv_dim)` == `len(config.conv_stride)` == `len(config.conv_kernel)`, but is `len(config.conv_dim) = z`, `len(config.conv_stride) = z`, `len(config.conv_kernel) = z`.N)rEr!rFr#r ValueErrorrIs rLvalidate_architecture)Data2VecAudioConfig.validate_architectures!! "d&B&B BD$$%)E)EEDMM"d&B&BB &''Ec$JZJZF[E\]//243C3C/D.ERI CrNcB[R"UR5$)N)mathprodr!rQs rLinputs_to_logits_ratio*Data2VecAudioConfig.inputs_to_logits_ratiosyy))**rN)rFrB)?__name__ __module__ __qualname____firstlineno____doc__ model_typer int__annotations__r rrrrstrrfloatrrrrrrrrrlisttupler!r#r$boolr&r(r)r*r+r,r-r.r/r1r2r3r5r6r8r9r:r;r<r=r>r?r@rArBrHrRpropertyrW__static_attributes__ __classcell__)rKs@rLr r sa F"JJKs!!!s!J"%NECK%&) )%(us{(%(us{(!$M53;$ Ius{ #u# NE #)S),OHd3i%S/)O/DKcU38_,D/EKcU38_,EIt)+!3+ "#"#$S$"&NECK&c  %(us{(!!"#C####t##(D( ###,FHd3i%S/)F/>KcU38_,>1@M49uS#X.@!! L#*  L#* +,L#S /D(,K  NC%)d )( ++rNr ) r]rUhuggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__rDrNrLrmsO! .3#>?h+*h+@h+V ! !rN