T^(h7pdZddlZddlZddlmZddlmZejeZ GddeZ dgZ y)zSEW model configurationN)PretrainedConfig)loggingceZdZdZdZ dfd ZedZxZS) SEWConfiga# This is the configuration class to store the configuration of a [`SEWModel`]. It is used to instantiate a SEW 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 SEW [asapp/sew-tiny-100k](https://huggingface.co/asapp/sew-tiny-100k) 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 SEW model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`SEW`]. 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. squeeze_factor (`int`, *optional*, defaults to 2): Sequence length downsampling factor after the encoder and upsampling factor after the transformer. 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 [`SEWForCTC`]. 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. conv_dim (`Tuple[int]` or `List[int]`, *optional*, defaults to `(64, 128, 128, 128, 128, 256, 256, 256, 256, 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, 1, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1)`): 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, 1, 3, 1, 3, 1, 3, 1, 2, 1, 2, 1)`): 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. 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'' 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 [`SEWForCTC`]. 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 [`SEWForCTC`]. 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. Example: ```python >>> from transformers import SEWConfig, SEWModel >>> # Initializing a SEW asapp/sew-tiny-100k style configuration >>> configuration = SEWConfig() >>> # Initializing a model (with random weights) from the asapp/sew-tiny-100k style configuration >>> model = SEWModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```sewc& t'|di|&|#|$|%d||_||_||_t ||_t ||_t ||_||_ ||_ ||_ t|j |_ ||_||_||_||_||_||_| |_| |_| |_| |_| |_||_||_||_t|j|jk7sDt|j|jk7s"t|j |jk7rNt9dt|j dt|jdt|jd||_||_||_||_ ||_!||_"||_#||_$| |_%|!|_&|"|_'y)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_sizesqueeze_factor hidden_actnum_attention_headshidden_dropoutattention_dropoutactivation_dropoutfeat_proj_dropout final_dropout layerdroplayer_norm_epsinitializer_range vocab_size ValueErrorapply_spec_augmentmask_time_probmask_time_lengthmask_time_min_masksmask_feature_probmask_feature_lengthmask_feature_min_masksctc_loss_reductionctc_zero_infinityuse_weighted_layer_sumclassifier_proj_size)(selfr)rrr rrrr!r#r"r$r%r&r(r'rrrrrrrrr+r,r-r.r/r0r1r2r3r4r5r r r kwargs __class__s( g/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/sew/configuration_sew.pyrzSEWConfig.__init__sR s6s $X  , ,"'>$-J*'*4=='9$!2!2,$#6 ,!2"4!2*",!2$!! "d&B&B BD$$%)E)EEDMM"d&B&BB225dmm2D1EF))*++I#dN^N^J_I``bd #5, 0#6 !2#6 &<##5!2'=#$8!c`tjtj|jdS)N) functoolsreduceoperatormulr)r6s r9inputs_to_logits_ratioz SEWConfig.inputs_to_logits_ratios! d.>.>BBr:)% i rCi gelu皙?rFrFrFrFg{Gz?gh㈵>grouprE) @rJrJrJrKrKrKrLrLrL) rDr<rDr<rDr<rDr<rDr<rDr<) rr<rr<rr<rr<rDr<rDr<FrJTg?rNrDrGrNrmeanFFrKrr<rD) __name__ __module__ __qualname____doc__ model_typerpropertyrA __classcell__)r8s@r9rrs{ zJ! &Q;< #&( !$ M^9@CCr:r) rTr=r?configuration_utilsrutilsr get_loggerrQloggerr__all__r r:r9r]sE3   H %bC bCJ -r: