gMNndZddlZddlZddlmZddlmZejeZ GddeZ dS)zWav2Vec2 model configurationN)PretrainedConfig)loggingceZdZdZdZ d%fd# Zed$ZxZS)&Wav2Vec2Configa3 This is the configuration class to store the configuration of a [`Wav2Vec2Model`]. It is used to instantiate an Wav2Vec2 model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Wav2Vec2 [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 32): Vocabulary size of the Wav2Vec2 model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`Wav2Vec2Model`] or [`TFWav2Vec2Model`]. Vocabulary size of the model. Defines the different tokens that can be represented by the *inputs_ids* passed to the forward method of [`Wav2Vec2Model`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. activation_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for activations inside the fully connected layer. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. final_dropout (`float`, *optional*, defaults to 0.1): The dropout probability for the final projection layer of [`Wav2Vec2ForCTC`]. layerdrop (`float`, *optional*, defaults to 0.1): The LayerDrop probability. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. feat_extract_norm (`str`, *optional*, defaults to `"group"`): The norm to be applied to 1D convolutional layers in feature encoder. One of `"group"` for group normalization of only the first 1D convolutional layer or `"layer"` for layer normalization of all 1D convolutional layers. feat_proj_dropout (`float`, *optional*, defaults to 0.0): The dropout probability for output of the feature encoder. 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. feat_quantizer_dropout (`float`, *optional*, defaults to 0.0): The dropout probability for quantized feature encoder states. 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_kernel (`Tuple[int]` or `List[int]`, *optional*, defaults to `(10, 3, 3, 3, 3, 3, 3)`): A tuple of integers defining the kernel size of each 1D convolutional layer in the feature encoder. The length of *conv_kernel* 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_embeddings (`int`, *optional*, defaults to 128): Number of convolutional positional embeddings. Defines the kernel size of 1D convolutional positional embeddings layer. num_conv_pos_embedding_groups (`int`, *optional*, defaults to 16): Number of groups of 1D convolutional positional embeddings layer. do_stable_layer_norm (`bool`, *optional*, defaults to `False`): Whether to apply *stable* layer norm architecture of the Transformer encoder. `do_stable_layer_norm is True` corresponds to applying layer norm before the attention layer, whereas `do_stable_layer_norm is False` corresponds to applying layer norm after the attention layer. apply_spec_augment (`bool`, *optional*, defaults to `True`): Whether to apply *SpecAugment* data augmentation to the outputs of the feature encoder. For reference see [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://arxiv.org/abs/1904.08779). 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 procecure generates ''mask_time_prob*len(time_axis)/mask_time_length'' independent masks over the axis. If reasoning from the propability 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 actual percentage of masked vectors. This is only relevant if `apply_spec_augment is True`. 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 procecure generates ''mask_feature_prob*len(feature_axis)/mask_time_length'' independent masks over the axis. If reasoning from the propability 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'' num_codevectors_per_group (`int`, *optional*, defaults to 320): Number of entries in each quantization codebook (group). num_codevector_groups (`int`, *optional*, defaults to 2): Number of codevector groups for product codevector quantization. contrastive_logits_temperature (`float`, *optional*, defaults to 0.1): The temperature *kappa* in the contrastive loss. feat_quantizer_dropout (`float`, *optional*, defaults to 0.0): The dropout probability for the output of the feature encoder that's used by the quantizer. num_negatives (`int`, *optional*, defaults to 100): Number of negative samples for the contrastive loss. codevector_dim (`int`, *optional*, defaults to 256): Dimensionality of the quantized feature vectors. proj_codevector_dim (`int`, *optional*, defaults to 256): Dimensionality of the final projection of both the quantized and the transformer features. diversity_loss_weight (`int`, *optional*, defaults to 0.1): The weight of the codebook diversity loss component. 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 [`Wav2Vec2ForCTC`]. 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 [`Wav2Vec2ForCTC`]. 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 [`Wav2Vec2ForSequenceClassification`]. 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 Wav2Vec2 Encoder. Can be very useful for warm-starting Wav2Vec2 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`. adapter_attn_dim (`int`, *optional*): Dimension of the attention adapter weights to be used in each attention block. An example of a model using attention adapters is [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all). 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 Wav2Vec2Config, Wav2Vec2Model >>> # Initializing a Wav2Vec2 facebook/wav2vec2-base-960h style configuration >>> configuration = Wav2Vec2Config() >>> # Initializing a model (with random weights) from the facebook/wav2vec2-base-960h style configuration >>> model = Wav2Vec2Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```wav2vec2  gelu皙?{Gz?h㈵>grouprrrrrrrrrrr rrrrrrFT皙?rrr@dsumrrrrirrrr#r#rrr#r#rr#rNc8 <tjdi|8|/|0|1d||_||_||_t ||_t ||_t ||_||_ ||_ ||_ t|j|_ ||_||_||_||_||_| |_||_| |_| |_| |_||_||_||_||_|)|_t|j|j ks:t|j|j kst|j|j krOt;dt|jdt|jdt|jd||_||_||_ ||_!||_"||_#||_$| |_%|!|_&|"|_'| |_(|#|_)|$|_*|%|_+|&|_,|'|_-|(|_.|2|_/|3|_0|4|_1|5|_2|6p||_3|7|_4|*|_5t |+|_6t |,|_7t |-|_8|.|_9dS)N) pad_token_id bos_token_id eos_token_idzConfiguration 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`.):super__init__ hidden_sizefeat_extract_normfeat_extract_activationlistconv_dim conv_stride conv_kernel conv_biasnum_conv_pos_embeddingsnum_conv_pos_embedding_groupslennum_feat_extract_layersnum_hidden_layersintermediate_size hidden_actnum_attention_headshidden_dropoutattention_dropoutactivation_dropoutfeat_proj_dropout final_dropout layerdroplayer_norm_epsinitializer_range vocab_sizedo_stable_layer_normuse_weighted_layer_sum ValueErrorapply_spec_augmentmask_time_probmask_time_lengthmask_time_min_masksmask_feature_probmask_feature_lengthmask_feature_min_masksnum_codevectors_per_groupnum_codevector_groupscontrastive_logits_temperaturefeat_quantizer_dropout num_negativescodevector_dimproj_codevector_dimdiversity_loss_weightctc_loss_reductionctc_zero_infinity add_adapteradapter_kernel_sizeadapter_stridenum_adapter_layersoutput_hidden_sizeadapter_attn_dimclassifier_proj_sizetdnn_dim tdnn_kernel tdnn_dilationxvector_output_dim):selfrDr,r8r;r9r:r<r>r=r?rRr@rArCrBr-r.r0r1r2r3r4r5rErHrIrJrKrLrMrNrOrPrQrSrTrUrVrWrXrFr_r`rarbrcr&r'r(rYrZr[r\r]r^kwargs __class__s: o/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/wav2vec2/configuration_wav2vec2.pyr+zWav2Vec2Config.__init__sv ss6s $X  ,, ,,"'>$-J*'*4='9'9$!2!2$#6 ,!2"4!2*",!2$$8!&<#! " "d&B B BD$%%)EEEDM""d&BBBI &&IIFI$JZF[F[II0343C/D/DIII #5, 0#6 !2#6 &<#*C&%:".L+&<#*,#6 %:"#5!2'#6 ,"4"4"C  0%9!X  ,,!-00"4cLtjtj|jdS)Nr#) functoolsreduceoperatormulr1)rds rginputs_to_logits_ratioz%Wav2Vec2Config.inputs_to_logits_ratioVs d.>BBBrh)7r r r r r r rrrrrrrrrrr rrrFrrFTrrrrrrrrrrrrrr FFrr!r"r$rrr#rFrrrNN) __name__ __module__ __qualname____doc__ model_typer+propertyrn __classcell__)rfs@rgrrs"l l \J"! &4)* #&(" "%'*! $ +#%qH5H5H5H5H5H5TCCXCCCCCrhr) rrrjrlconfiguration_utilsrutilsr get_loggerrologgerrr)rhrgrzs#"333333  H % %}C}C}C}C}C%}C}C}C}C}Crh