i.3zdZddlZddlZddlmZddlmZddlmZedeGd d eZ d gZ y) zWavLM model configurationN)strict)PreTrainedConfig)auto_docstringzmicrosoft/wavlm-base) checkpointceZdZUdZdZdZeed<dZeed<dZ eed<dZ eed <d Z eed <d Z e ed <dZeezed<dZeezed<dZeezed<dZeezed<dZeezed<dZeezed<dZeed<dZeed<dZe ed<d Ze ed<dZeeeedfzed<d Zeeeedfzed!<d"Zeeeedfzed#<d$Zeed%<d&Z eed'<d(Z!eed)<d*Z"eed+<d,Z#eed-<d$Z$eed.<d/Z%eed0<d1Z&eezed2<d3Z'eed4<d5Z(eed6<dZ)eezed7<d3Z*eed8<d*Z+eed9<d5Z,eed:<dZ-eed;<dZ/eed?<d>Z0eed@<dZ1eedA<dBZ2e edC<d$Z3eedD<d$Z4eedE<d>Z5eedF<dGZ6eeeedfzedH<dIZ7eeeedfzedJ<dKZ8eeeedfzedL<dMZ9eedN<dOZ:eedP<dQZ;edRzedS<dTZeedW<dXZ?eedY<d5Z@eedZ<dXZAeed[<dRZBedRzed\<fd]ZCd^ZDeEd_ZFxZGS)` WavLMConfigaW" 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 [`WavLMForCTC`]. 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, 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. num_buckets (`int`, *optional*, defaults to 320): The number of buckets to use for each attention layer max_bucket_distance (`int`, *optional*, defaults to 800): Maximum bucket distance 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://huggingface.co/papers/1904.08779). mask_time_prob (`float`, *optional*, defaults to 0.05): Probability of each feature vector along the time axis to be chosen as the start of the vector span to be masked. Approximately `mask_time_prob * sequence_length // mask_time_length` feature vectors will be masked along the time axis. 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): Probability of each feature vector along the feature axis to be chosen as the start of the vector span to be masked. Approximately `mask_time_prob * hidden_size // mask_time_length` feature vectors will be masked along the time axis. 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. 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_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 [`WavLMForCTC`]. 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 [`WavLMForSequenceClassification`]. 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. 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`]. 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`. 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 ``` Example: ```python >>> from transformers import WavLMConfig, WavLMModel >>> # Initializing a WavLM facebook/wavlm-base-960h style configuration >>> configuration = WavLMConfig() >>> # Initializing a model (with random weights) from the facebook/wavlm-base-960h style configuration >>> model = WavLMModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```wavlm 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_epsgroupfeat_extract_normfeat_extract_activation)rrrrrr.conv_dim)r"r"r"r"r" conv_stride) rrrrr"r" conv_kernelF conv_biasnum_conv_pos_embeddingsnum_conv_pos_embedding_groupsi@ num_bucketsi max_bucket_distancedo_stable_layer_normTapply_spec_augmentg?mask_time_probr$mask_time_lengthr"mask_time_min_masksmask_feature_probmask_feature_lengthnum_codevectors_per_groupnum_codevector_groupscontrastive_logits_temperatured num_negativescodevector_dimproj_codevector_dimdiversity_loss_weightmeanctc_loss_reductionctc_zero_infinityuse_weighted_layer_sumclassifier_proj_size)rrrritdnn_dim)r!rrrC tdnn_kernel)rCr"rrCrC tdnn_dilationrxvector_output_dimPnum_ctc_classesrN pad_token_idrC bos_token_id eos_token_id add_adapterradapter_kernel_sizeadapter_stridenum_adapter_layersoutput_hidden_sizec t|j|_|jxs |j|_t |di|y)N)lenr num_feat_extract_layersrPr super __post_init__)selfkwargs __class__s ~/var/www/vps2.regionflexible.com/Desarrollo/venv/lib/python3.12/site-packages/transformers/models/wavlm/configuration_wavlm.pyrVzWavLMConfig.__post_init__s='*4=='9$"&"9"9"MT=M=M ''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)rSr#rTr%r ValueErrorrWs rZvalidate_architecturez!WavLMConfig.validate_architectures!! "d&B&B BD$$%)E)EEDMM"d&B&BB &''Ec$JZJZF[E\]//243C3C/D.ERI Cr[c`tjtj|jdS)NrC) functoolsreduceoperatormulr#r^s rZinputs_to_logits_ratioz"WavLMConfig.inputs_to_logits_ratios! d.>.>BBr[)H__name__ __module__ __qualname____doc__ model_typer int__annotations__r rrrrstrrfloatrrrrrrrrrr listtupler#r%r&boolr(r*r+r,r-r.r/r0r1r2r3r4r5r6r8r:r;r<r>r?r@rArBrDrErFrHrIrJrKrLrMrNrOrPrVr_propertyre __classcell__)rYs@rZr r s BJJKs!!!s!J"%NECK%&) )%(us{(%(us{(!$M53;$ Ius{ #u# NE $s$#)S),OHd3i%S/)O/DKcU38_,D/EKcU38_,EIt#&S&)+!3+K""!&$&##"&NECK&c  %(us{(!!%(s(!"3",/"E/M3NC""#&5&$$#t##(D( ###,FHd3i%S/)F/>KcU38_,>1@M49uS#X.@!!OS L#*  L#* +,L#S /D(,K  NC%)d )( CCr[r ) rirarchuggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__rRr[rZrxsS .3#12QC"QC3QCh /r[