# Copyright 2021 The Fairseq Authors, Microsoft Research, and The HuggingFace Inc. team. All rights reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. """WavLM model configuration""" import functools import operator from huggingface_hub.dataclasses import strict from ...configuration_utils import PreTrainedConfig from ...utils import auto_docstring @auto_docstring(checkpoint="microsoft/wavlm-base") @strict class WavLMConfig(PreTrainedConfig): r""" 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 ```""" model_type = "wavlm" vocab_size: int = 32 hidden_size: int = 768 num_hidden_layers: int = 12 num_attention_heads: int = 12 intermediate_size: int = 3072 hidden_act: str = "gelu" hidden_dropout: float | int = 0.1 activation_dropout: float | int = 0.1 attention_dropout: float | int = 0.1 feat_proj_dropout: float | int = 0.0 final_dropout: float | int = 0.1 layerdrop: float | int = 0.1 initializer_range: float = 0.02 layer_norm_eps: float = 1e-5 feat_extract_norm: str = "group" feat_extract_activation: str = "gelu" conv_dim: list[int] | tuple[int, ...] = (512, 512, 512, 512, 512, 512, 512) conv_stride: list[int] | tuple[int, ...] = (5, 2, 2, 2, 2, 2, 2) conv_kernel: list[int] | tuple[int, ...] = (10, 3, 3, 3, 3, 2, 2) conv_bias: bool = False num_conv_pos_embeddings: int = 128 num_conv_pos_embedding_groups: int = 16 num_buckets: int = 320 max_bucket_distance: int = 800 do_stable_layer_norm: bool = False apply_spec_augment: bool = True mask_time_prob: float | int = 0.05 mask_time_length: int = 10 mask_time_min_masks: int = 2 mask_feature_prob: float | int = 0.0 mask_feature_length: int = 10 num_codevectors_per_group: int = 320 num_codevector_groups: int = 2 contrastive_logits_temperature: float = 0.1 num_negatives: int = 100 codevector_dim: int = 256 proj_codevector_dim: int = 256 diversity_loss_weight: float = 0.1 ctc_loss_reduction: str = "mean" ctc_zero_infinity: bool = False use_weighted_layer_sum: bool = False classifier_proj_size: int = 256 tdnn_dim: list[int] | tuple[int, ...] = (512, 512, 512, 512, 1500) tdnn_kernel: list[int] | tuple[int, ...] = (5, 3, 3, 1, 1) tdnn_dilation: list[int] | tuple[int, ...] = (1, 2, 3, 1, 1) xvector_output_dim: int = 512 num_ctc_classes: int = 80 pad_token_id: int | None = 0 bos_token_id: int | None = 1 eos_token_id: int | list[int] | None = 2 add_adapter: bool = False adapter_kernel_size: int = 3 adapter_stride: int = 2 num_adapter_layers: int = 3 output_hidden_size: int | None = None def __post_init__(self, **kwargs): self.num_feat_extract_layers = len(self.conv_dim) self.output_hidden_size = self.output_hidden_size or self.hidden_size super().__post_init__(**kwargs) def validate_architecture(self): """Part of `@strict`-powered validation. Validates the architecture of the config.""" 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)}`." ) @property def inputs_to_logits_ratio(self): return functools.reduce(operator.mul, self.conv_stride, 1) __all__ = ["WavLMConfig"]