i%zdZddlZddlZddlmZddlmZddlmZedeGd d eZ d gZ y) zSEW model configurationN)strict)PreTrainedConfig)auto_docstringzBAAI/seggpt-vit-large) checkpointceZdZUdZdZdZeed<dZeed<dZ eed<dZ eed <d Z eed <d Z eed <dZ eed<dZeezed<dZeezed<dZeezed<dZeezed<dZeezed<dZeezed<dZeed<dZeed<dZeed<dZeed<dZeeeed fzed!<d"Zeeeed fzed#<d$Zeeeed fzed%<d&Ze ed'<d(Z!eed)<d*Z"eed+<d,Z#e ed-<d.Z$eezed/<d0Z%eed1<d Z&eed2<dZ'eezed3<d0Z(eed4<d5Z)eed6<d7Z*eed8<d&Z+e ed9<d&Z,e ed:<d;Z-eed<<d5Z.ed=zed><d?Z/ed=zed@<d Z0eeezd=zedA<fdBZ1dCZ2e3dDZ4xZ5S)E SEWConfiga squeeze_factor (`int`, *optional*, defaults to 2): Sequence length downsampling factor after the encoder and upsampling factor after the transformer. 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 [`SEWForCTC`]. 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_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://huggingface.co/papers/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 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 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 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_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 ```sew vocab_sizei hidden_size num_hidden_layersnum_attention_headsi intermediate_sizesqueeze_factorgelu hidden_actg?hidden_dropoutactivation_dropoutattention_dropoutgfeat_proj_dropout final_dropout layerdropg{Gz?initializer_rangegh㈵>layer_norm_epsgroupfeat_extract_normfeat_extract_activation) @r"r"r"r#r#r#r$r$r$.conv_dim) rrr'rr'rr'rr'rr' conv_stride) rr'rr'rr'rr'rr'rr' conv_kernelF conv_biasr"num_conv_pos_embeddingsnum_conv_pos_embedding_groupsTapply_spec_augmentg?mask_time_probr)mask_time_lengthmask_time_min_masksmask_feature_probmask_feature_lengthrmask_feature_min_masksmeanctc_loss_reductionctc_zero_infinityuse_weighted_layer_sumr#classifier_proj_sizeN pad_token_idr' bos_token_id eos_token_idc Xt|j|_t|di|y)N)lenr%num_feat_extract_layerssuper __post_init__)selfkwargs __class__s z/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/transformers/models/sew/configuration_sew.pyrCzSEWConfig.__post_init__s$'*4=='9$ ''c lt|j|jk7sDt|j|jk7s"t|j|jk7rNt dt|jdt|jdt|jdy)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)r@r(rAr*r% ValueErrorrDs rGvalidate_architecturezSEWConfig.validate_architectures!! "d&B&B BD$$%)E)EEDMM"d&B&BB225dmm2D1EF))*++I#dN^N^J_I``bd CrHc`tjtj|jdS)Nr') functoolsreduceoperatormulr(rKs rGinputs_to_logits_ratioz SEWConfig.inputs_to_logits_ratios! d.>.>BBrH)6__name__ __module__ __qualname____doc__ model_typer int__annotations__r rrrrrstrrfloatrrrrrrrrr r%listtupler(r*r+boolr,r.r/r0r1r2r3r4r5r7r8r9r:r;r<r=rCrLpropertyrR __classcell__)rFs@rGr r s S jJJKs!!!s!NCJ"%NECK%&) )%(us{(%(us{(!$M53;$ Ius{ #u# NE $s$#)S),lHd3i%S/)l/VKcU38_,V/WKcU38_,WIt#&S&)+!3+##"&NECK&c  %(us{(!!"#C#$$#t##(D( ### L#*  L#* +,L#S /D(,( CCrHr ) rVrNrPhuggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__r?rHrGresS.3#23RC RC4RCj -rH