"""WavLM model configuration""" import functools import operator from transformers.configuration_utils import PretrainedConfig from transformers.utils import logging logger = logging.get_logger(__name__) class WavLMSpkRegConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a [`WavLMModel`]. It is used to instantiate an WavLM 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 WavLM [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) 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 WavLM model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`WavLMModel`]. Vocabulary size of the model. Defines the different tokens that can be represented by the *inputs_ids* passed to the forward method of [`WavLMModel`]. 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 [`WavLMForCTC`]. 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 `(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): Propability 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): Propability 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_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 [`WavLMForCTC`]. 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. 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 ```""" model_type = "wavlm" def __init__( self, vocab_size=32, hidden_size=768, num_hidden_layers=12, num_attention_heads=12, intermediate_size=3072, hidden_act="gelu", hidden_dropout=0.1, activation_dropout=0.1, attention_dropout=0.1, feat_proj_dropout=0.0, final_dropout=0.1, layerdrop=0.1, initializer_range=0.02, layer_norm_eps=1e-5, feat_extract_norm="group", feat_extract_activation="gelu", conv_dim=(512, 512, 512, 512, 512, 512, 512), conv_stride=(5, 2, 2, 2, 2, 2, 2), conv_kernel=(10, 3, 3, 3, 3, 2, 2), conv_bias=False, num_conv_pos_embeddings=128, num_conv_pos_embedding_groups=16, num_buckets=320, max_bucket_distance=800, do_stable_layer_norm=False, apply_spec_augment=True, mask_time_prob=0.05, mask_time_length=10, mask_time_min_masks=2, mask_feature_prob=0.0, mask_feature_length=10, num_codevectors_per_group=320, num_codevector_groups=2, contrastive_logits_temperature=0.1, num_negatives=100, codevector_dim=256, proj_codevector_dim=256, diversity_loss_weight=0.1, ctc_loss_reduction="mean", ctc_zero_infinity=False, use_weighted_layer_sum=False, classifier_proj_size=256, tdnn_dim=(512, 512, 512, 512, 1500), tdnn_kernel=(5, 3, 3, 1, 1), tdnn_dilation=(1, 2, 3, 1, 1), xvector_output_dim=512, num_ctc_classes=80, pad_token_id=0, bos_token_id=1, eos_token_id=2, add_adapter=False, adapter_kernel_size=3, adapter_stride=2, num_adapter_layers=3, output_hidden_size=None, loss_fct: str = 'cross_entropy', # cross_entropy, additive_margin, additive_angular_margin label_smoothing: float = 0.0, scale: float = 30.0, margin: float = 0.35, easy_margin: bool = False, reduction: str = "mean", **kwargs, ): super().__init__(**kwargs, pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id) self.hidden_size = hidden_size self.feat_extract_norm = feat_extract_norm self.feat_extract_activation = feat_extract_activation self.conv_dim = list(conv_dim) self.conv_stride = list(conv_stride) self.conv_kernel = list(conv_kernel) self.conv_bias = conv_bias self.num_buckets = num_buckets self.max_bucket_distance = max_bucket_distance self.num_conv_pos_embeddings = num_conv_pos_embeddings self.num_conv_pos_embedding_groups = num_conv_pos_embedding_groups self.num_feat_extract_layers = len(self.conv_dim) self.num_hidden_layers = num_hidden_layers self.intermediate_size = intermediate_size self.hidden_act = hidden_act self.num_attention_heads = num_attention_heads self.hidden_dropout = hidden_dropout self.attention_dropout = attention_dropout self.activation_dropout = activation_dropout self.feat_proj_dropout = feat_proj_dropout self.final_dropout = final_dropout self.layerdrop = layerdrop self.layer_norm_eps = layer_norm_eps self.initializer_range = initializer_range self.num_ctc_classes = num_ctc_classes self.vocab_size = vocab_size self.do_stable_layer_norm = do_stable_layer_norm self.use_weighted_layer_sum = use_weighted_layer_sum self.classifier_proj_size = classifier_proj_size if ( (len(self.conv_stride) != self.num_feat_extract_layers) or (len(self.conv_kernel) != self.num_feat_extract_layers) or (len(self.conv_dim) != self.num_feat_extract_layers) ): raise ValueError( "Configuration 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) =" f" {len(self.conv_dim)}`, `len(config.conv_stride) = {len(self.conv_stride)}`," f" `len(config.conv_kernel) = {len(self.conv_kernel)}`." ) # fine-tuning config parameters for SpecAugment: https://arxiv.org/abs/1904.08779 self.apply_spec_augment = apply_spec_augment self.mask_time_prob = mask_time_prob self.mask_time_length = mask_time_length self.mask_time_min_masks = mask_time_min_masks self.mask_feature_prob = mask_feature_prob self.mask_feature_length = mask_feature_length # parameters for pretraining with codevector quantized representations self.num_codevectors_per_group = num_codevectors_per_group self.num_codevector_groups = num_codevector_groups self.contrastive_logits_temperature = contrastive_logits_temperature self.num_negatives = num_negatives self.codevector_dim = codevector_dim self.proj_codevector_dim = proj_codevector_dim self.diversity_loss_weight = diversity_loss_weight # ctc loss self.ctc_loss_reduction = ctc_loss_reduction self.ctc_zero_infinity = ctc_zero_infinity # adapter self.add_adapter = add_adapter self.adapter_kernel_size = adapter_kernel_size self.adapter_stride = adapter_stride self.num_adapter_layers = num_adapter_layers self.output_hidden_size = output_hidden_size or hidden_size # SequenceClassification-specific parameter. Feel free to ignore for other classes. self.classifier_proj_size = classifier_proj_size # XVector-specific parameters. Feel free to ignore for other classes. self.tdnn_dim = list(tdnn_dim) self.tdnn_kernel = list(tdnn_kernel) self.tdnn_dilation = list(tdnn_dilation) self.xvector_output_dim = xvector_output_dim # Loss function parameters. Feel free to ignore for other classes. self.loss_fct = loss_fct self.label_smoothing = label_smoothing self.scale = scale self.margin = margin self.easy_margin = easy_margin self.reduction = reduction @property def inputs_to_logits_ratio(self): return functools.reduce(operator.mul, self.conv_stride, 1)