
    ^jZ+                     r    d Z ddlZddlmZ ddlmZ ddlmZ  ed      e G d	 d
e                    Zd
gZ	y)zData2VecText configuration    N)strict   )PreTrainedConfig)auto_docstringz!facebook/data2vec-audio-base-960h)
checkpointc                   ~    e Zd ZU dZdZdZeed<   dZeed<   dZ	eed<   dZ
eed	<   d
Zeed<   dZeed<   dZeez  ed<   dZeez  ed<   dZeez  ed<   dZeez  ed<   dZeez  ed<   dZeez  ed<   dZeed<   dZeed<   dZeed<   dZee   eedf   z  ed<   dZee   eedf   z  ed<   d Zee   eedf   z  ed!<   d"Zeed#<   d$Zeed%<   d&Z eed'<   d(Z!eed)<   d*Z"eez  ed+<   d,Z#eed-<   d.Z$eed/<   dZ%eez  ed0<   d,Z&eed1<   d2Z'eed3<   d4Z(eed5<   d"Z)eed6<   d"Z*eed7<   d8Z+eed9<   d:Z,ee   eedf   z  ed;<   d<Z-ee   eedf   z  ed=<   d>Z.ee   eedf   z  ed?<   d@Z/eedA<   d2Z0edBz  edC<   dDZ1edBz  edE<   d.Z2eee   z  dBz  edF<   d"Z3eedG<   dHZ4eedI<   d.Z5eedJ<   dHZ6eedK<   dBZ7edBz  edL<    fdMZ8dN Z9e:dO        Z; xZ<S )PData2VecAudioConfiga?  
    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 [`Data2VecAudioForCTC`].
    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_bias (`bool`, *optional*, defaults to `False`):
        Whether the 1D convolutional layers have a bias.
    num_conv_pos_embedding_groups (`int`, *optional*, defaults to 16):
        Number of groups of 1D convolutional positional embeddings layer.
    conv_pos_kernel_size (`int`, *optional*, defaults to `19`):
        Kernel size of positional conv module.
    num_conv_pos_embeddings (`int`, *optional*, defaults to 128):
        Number of convolutional positional embeddings. Defines the kernel size of 1D convolutional positional
        embeddings layer.
    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
    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_loss_reduction (`str`, *optional*, defaults to `"sum"`):
        Specifies the reduction to apply to the output of `torch.nn.CTCLoss`. Only relevant when training an
        instance of [`Data2VecAudioForCTC`].
    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 [`Data2VecAudioForCTC`].
    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 [`Data2VecAudioForSequenceClassification`].
    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 Data2VecAudio Encoder. Can be very useful
        for warm-starting Data2VecAudio 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
    >>> from transformers import Data2VecAudioConfig, Data2VecAudioModel

    >>> # Initializing a Data2VecAudio facebook/data2vec-audio-base-960h style configuration
    >>> configuration = Data2VecAudioConfig()

    >>> # Initializing a model (with random weights) from the facebook/data2vec-audio-base-960h style configuration
    >>> model = Data2VecAudioModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```zdata2vec-audio    
vocab_sizei   hidden_size   num_hidden_layersnum_attention_headsi   intermediate_sizegelu
hidden_actg?hidden_dropoutactivation_dropoutattention_dropoutg        feat_proj_dropoutfinal_dropout	layerdropg{Gz?initializer_rangegh㈵>layer_norm_epsfeat_extract_activation)   r   r   r   r   r   r   .conv_dim)      r   r   r   r   r   conv_stride)
   r   r   r   r   r   r   conv_kernelF	conv_bias   num_conv_pos_embedding_groups   conv_pos_kernel_sizer   num_conv_pos_embeddingsg?mask_time_probr!   mask_time_lengthr   mask_time_min_masksmask_feature_probmask_feature_lengthr   mask_feature_min_maskssumctc_loss_reductionctc_zero_infinityuse_weighted_layer_sum   classifier_proj_size)r   r   r   r   i  tdnn_dim)r   r   r      r6   tdnn_kernel)r6   r   r   r6   r6   tdnn_dilationr   xvector_output_dimNpad_token_idr6   bos_token_ideos_token_idadd_adapterr   adapter_kernel_sizeadapter_stridenum_adapter_layersoutput_hidden_sizec                     | j                   xs | j                  | _         t        | j                        | _        t        |   di | y )N )rA   r   lenr   num_feat_extract_layerssuper__post_init__)selfkwargs	__class__s     /var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/data2vec/configuration_data2vec_audio.pyrG   z!Data2VecAudioConfig.__post_init__   s=    "&"9"9"MT=M=M'*4=='9$''    c           
      l   t        | j                        | j                  k7  sDt        | j                        | j                  k7  s"t        | j                        | j                  k7  rNt        dt        | j                         dt        | j                         dt        | j                         d      y)zOPart of `@strict`-powered validation. Validates the architecture of the config.zConfiguration for convolutional layers is incorrect. It is required that `len(config.conv_dim)` == `len(config.conv_stride)` == `len(config.conv_kernel)`, but is `len(config.conv_dim) = z`, `len(config.conv_stride) = z`, `len(config.conv_kernel) = z`.N)rD   r    rE   r"   r   
ValueErrorrH   s    rK   validate_architecturez)Data2VecAudioConfig.validate_architecture   s     !!"d&B&BBD$$%)E)EEDMM"d&B&BB&''Ec$JZJZF[E\ ]//243C3C/D.ERI  CrL   c                 @    t        j                  | j                        S )N)mathprodr    rO   s    rK   inputs_to_logits_ratioz*Data2VecAudioConfig.inputs_to_logits_ratio   s    yy))**rL   )=__name__
__module____qualname____doc__
model_typer   int__annotations__r   r   r   r   r   strr   floatr   r   r   r   r   r   r   r   r   listtupler    r"   r#   boolr%   r'   r(   r)   r*   r+   r,   r-   r.   r0   r1   r2   r4   r5   r7   r8   r9   r:   r;   r<   r=   r>   r?   r@   rA   rG   rP   propertyrT   __classcell__)rJ   s   @rK   r	   r	      s   aF "JJKs!!!s!J"%NECK%&))%(us{(%(us{(!$M53;$ Ius{ #u# NE #)S),OHd3i%S/)O/DKcU38_,D/EKcU38_,EIt)+!3+ "#"#$S$"&NECK&c  %(us{(!!"#C####t##(D( ###,FHd3i%S/)F/>KcU38_,>1@M49uS#X.@!! L#*  L#* +,L#S	/D(,K  NC%)d
)(
 + +rL   r	   )
rX   rR   huggingface_hub.dataclassesr   configuration_utilsr   utilsr   r	   __all__rC   rL   rK   <module>rg      sO    !  . 3 # >?h+* h+  @h+V !
!rL   