g.DndZddlZddlZddlmZddlmZejeZ GddeZ dS)zUniSpeech model configurationN)PretrainedConfig)loggingceZdZdZdZ d!fd Zed ZxZS)"UniSpeechConfiga, This is the configuration class to store the configuration of a [`UniSpeechModel`]. It is used to instantiate an UniSpeech 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 UniSpeech [microsoft/unispeech-large-1500h-cv](https://huggingface.co/microsoft/unispeech-large-1500h-cv) 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 UniSpeech model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`UniSpeechModel`]. Vocabulary size of the model. Defines the different tokens that can be represented by the *inputs_ids* passed to the forward method of [`UniSpeechModel`]. 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. feat_proj_dropout (`float`, *optional*, defaults to 0.0): The dropout probability for output of the feature encoder. 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. final_dropout (`float`, *optional*, defaults to 0.1): The dropout probability for the final projection layer of [`UniSpeechForCTC`]. 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-05): 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_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_kernel (`Tuple[int]` or `List[int]`, *optional*, defaults to `(10, 3, 3, 3, 3, 2, 2)`): 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. 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 `"mean"`): Specifies the reduction to apply to the output of `torch.nn.CTCLoss`. Only relevant when training an instance of [`UniSpeechForCTC`]. 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 [`UniSpeechForCTC`]. 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 [`UniSpeechForSequenceClassification`]. classifier_proj_size (`int`, *optional*, defaults to 256): Dimensionality of the projection before token mean-pooling for classification. num_ctc_classes (`int`, *optional*, defaults to 80): Specifies the number of classes (phoneme tokens and blank token) for phoneme-level CTC loss. Only relevant when using an instance of [`UniSpeechForPreTraining`]. pad_token_id (`int`, *optional*, defaults to 0): The id of the padding token. bos_token_id (`int`, *optional*, defaults to 1): The id of the "beginning-of-sequence" token. eos_token_id (`int`, *optional*, defaults to 2): The id of the "end-of-sequence" token. replace_prob (`float`, *optional*, defaults to 0.5): Propability that transformer feature is replaced by quantized feature for pretraining. Example: ```python >>> from transformers import UniSpeechConfig, UniSpeechModel >>> # Initializing a UniSpeech facebook/unispeech-base-960h style configuration >>> configuration = UniSpeechConfig() >>> # Initializing a model (with random weights) from the facebook/unispeech-base-960h style configuration >>> model = UniSpeechModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` unispeech  gelu皙?{Gz?h㈵>grouprrrrrrrrrrr rrrrrrFT皙?rrr@dmeanP?c0 ztjdi|0|,|-|.d||_||_||_t ||_t ||_t ||_||_ ||_ ||_ t|j|_ ||_||_||_||_||_| |_||_| |_| |_| |_||_||_|+|_||_||_|)|_|*|_t|j|j ks:t|j|j kst|j|j krOt?dt|jdt|jdt|jd||_ ||_!||_"||_#||_$||_%||_&| |_'|!|_(|"|_)| |_*|#|_+|$|_,|%|_-|&|_.|'|_/|(|_0|/|_1dS)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`.)2super__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_rangenum_ctc_classes vocab_sizedo_stable_layer_normuse_weighted_layer_sumclassifier_proj_size 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 replace_prob)2selfrDr+r7r:r8r9r;r=r<r>rSr?r@rBrAr,r-r/r0r1r2r3r4rErIrJrKrLrMrNrOrPrQrRrTrUrVrWrXrYrFrGrCr%r&r'rZkwargs __class__s2 q/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/unispeech/configuration_unispeech.pyr*zUniSpeechConfig.__init__s~f ss6s $X  ,, ,,"'>$-J*'*4='9'9$!2!2$#6 ,!2"4!2*",!2.$$8!&<#$8!! " "d&B B BD$%%)EEEDM""d&BBBI &&IIFI$JZF[F[II0343C/D/DIII #5, 0#6 !2#6 &<#*C&%:".L+&<#*,#6 %:"#5!2)cLtjtj|jdS)Nr") functoolsreduceoperatormulr0)r[s r^inputs_to_logits_ratioz&UniSpeechConfig.inputs_to_logits_ratio0s d.>BBBr_)/r r r r r r rrrrrrrrrrr rrrFrrFTrrrrrrrrrrrrrr FFrr!rr"rr#) __name__ __module__ __qualname____doc__ model_typer*propertyre __classcell__)r]s@r^rrs Z Z xJ"! &4)* #&(" "%'*!!$ at)t)t)t)t)t)lCCXCCCCCr_r) rirarcconfiguration_utilsrutilsr get_loggerrfloggerrr(r_r^rqs$#333333  H % %WCWCWCWCWC&WCWCWCWCWCr_