§
    9²¸jZ+  ã                   óŒ   — 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	dS )zData2VecText configurationé    N)Ústricté   )ÚPreTrainedConfig)Úauto_docstringz!facebook/data2vec-audio-base-960h)Ú
checkpointc                   óÒ  ‡ — 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<   ˆ fdM„Z8dN„ Z9e:dO„ ¦   «         Z;ˆ xZ<S )PÚ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-audioé    Ú
vocab_sizei   Úhidden_sizeé   Únum_hidden_layersÚnum_attention_headsi   Úintermediate_sizeÚgeluÚ
hidden_actgš™™™™™¹?Úhidden_dropoutÚactivation_dropoutÚattention_dropoutg        Úfeat_proj_dropoutÚfinal_dropoutÚ	layerdropg{®Gáz”?Úinitializer_rangegñhãˆµøä>Úlayer_norm_epsÚfeat_extract_activation)é   r   r   r   r   r   r   .Úconv_dim)é   é   r   r   r   r   r   Úconv_stride)é
   r   r   r   r   r   r   Úconv_kernelFÚ	conv_biasé   Únum_conv_pos_embedding_groupsé   Úconv_pos_kernel_sizer   Únum_conv_pos_embeddingsgš™™™™™©?Úmask_time_probr!   Úmask_time_lengthr   Úmask_time_min_masksÚmask_feature_probÚmask_feature_lengthr   Úmask_feature_min_masksÚsumÚctc_loss_reductionÚctc_zero_infinityÚuse_weighted_layer_sumé   Úclassifier_proj_size)r   r   r   r   iÜ  Útdnn_dim)r   r   r   é   r6   Útdnn_kernel)r6   r   r   r6   r6   Útdnn_dilationr   Úxvector_output_dimNÚpad_token_idr6   Úbos_token_idÚeos_token_idÚadd_adapterr   Úadapter_kernel_sizeÚadapter_strideÚnum_adapter_layersÚoutput_hidden_sizec                 ó’   •— | j         p| j        | _         t          | j        ¦  «        | _         t          ¦   «         j        di |¤Ž d S )N© )rA   r   Úlenr   Únum_feat_extract_layersÚsuperÚ__post_init__)ÚselfÚkwargsÚ	__class__s     €ú‰/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/data2vec/configuration_data2vec_audio.pyrG   z!Data2VecAudioConfig.__post_init__­   sK   ø€ Ø"&Ô"9Ð"M¸TÔ=MˆÔÝ'*¨4¬=Ñ'9Ô'9ˆÔ$Ø�‰ŒÔÐ'Ð' Ð'Ð'Ð'Ð'Ð'ó    c           
      óR  — t          | j        ¦  «        | j        k    s:t          | j        ¦  «        | j        k    st          | j        ¦  «        | j        k    rOt          dt          | j        ¦  «        › dt          | j        ¦  «        › dt          | j        ¦  «        › d�¦  «        ‚dS )zOPart of `@strict`-powered validation. Validates the architecture of the config.zºConfiguration for convolutional layers is incorrect. It is required that `len(config.conv_dim)` == `len(config.conv_stride)` == `len(config.conv_kernel)`, but is `len(config.conv_dim) = z`, `len(config.conv_stride) = z`, `len(config.conv_kernel) = z`.N)rD   r    rE   r"   r   Ú
ValueError©rH   s    rK   Úvalidate_architecturez)Data2VecAudioConfig.validate_architecture²   sÄ   € õ �Ô!Ñ"Ô" dÔ&BÒBÐBÝ�DÔ$Ñ%Ô%¨Ô)EÒEÐEÝ�D”MÑ"Ô" dÔ&BÒBÐBåðIå˜œÑ&Ô&ðIð IåFIÈ$ÔJZÑF[ÔF[ðIð Iõ 03°4Ô3CÑ/DÔ/DðIð Ið Iñô ð ð CÐBrL   c                 ó4   — t          j        | j        ¦  «        S )N)ÚmathÚprodr    rO   s    rK   Úinputs_to_logits_ratioz*Data2VecAudioConfig.inputs_to_logits_ratioÀ   s   € åŒy˜Ô)Ñ*Ô*Ð*rL   )=Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typer   ÚintÚ__annotations__r   r   r   r   r   Ústrr   Úfloatr   r   r   r   r   r   r   r   r   ÚlistÚtupler    r"   r#   Úboolr%   r'   r(   r)   r*   r+   r,   r-   r.   r0   r1   r2   r4   r5   r7   r8   r9   r:   r;   r<   r=   r>   r?   r@   rA   rG   rP   ÚpropertyrT   Ú__classcell__)rJ   s   @rK   r	   r	      sï  ø€ € € € € € ðað aðF "€Jà€J�ÐÐÑØ€K�ÐÐÑØÐ�sÐÐÑØ!Ð˜Ð!Ð!Ñ!Ø!Ð�sÐ!Ð!Ñ!Ø€J�ÐÐÑØ"%€N�E˜C‘KÐ%Ð%Ñ%Ø&)Ð˜ ™Ð)Ð)Ñ)Ø%(Ð�u˜s‘{Ð(Ð(Ñ(Ø%(Ð�u˜s‘{Ð(Ð(Ñ(Ø!$€M�5˜3‘;Ð$Ð$Ñ$Ø €Iˆu�s‰{Ð Ð Ñ Ø#Ð�uÐ#Ð#Ñ#Ø €N�EÐ Ð Ñ Ø#)Ð˜SÐ)Ð)Ñ)Ø,O€Hˆd�3Œi˜%  S œ/Ñ)ÐOÐOÑOØ/D€K��c”˜U 3¨ 8œ_Ñ,ÐDÐDÑDØ/E€K��c”˜U 3¨ 8œ_Ñ,ÐEÐEÑEØ€IˆtÐÐÑØ)+Ð! 3Ð+Ð+Ñ+Ø "Ð˜#Ð"Ð"Ñ"Ø#$Ð˜SÐ$Ð$Ñ$Ø"&€N�E˜C‘KÐ&Ð&Ñ&ØÐ�cÐÐÑØ Ð˜Ð Ð Ñ Ø%(Ð�u˜s‘{Ð(Ð(Ñ(Ø!Ð˜Ð!Ð!Ñ!Ø"#Ð˜CÐ#Ð#Ñ#Ø#Ð˜Ð#Ð#Ñ#Ø#Ð�tÐ#Ð#Ñ#Ø#(Ð˜DÐ(Ð(Ñ(Ø #Ð˜#Ð#Ð#Ñ#Ø,F€Hˆd�3Œi˜%  S œ/Ñ)ÐFÐFÑFØ/>€K��c”˜U 3¨ 8œ_Ñ,Ð>Ð>Ñ>Ø1@€M�4˜”9˜u S¨# XœÑ.Ð@Ð@Ñ@Ø!Ð˜Ð!Ð!Ñ!Ø €L�#˜‘*Ð Ð Ñ Ø €L�#˜‘*Ð Ð Ñ Ø+,€L�#˜˜Sœ	‘/ DÑ(Ð,Ð,Ñ,Ø€K�ÐÐÑØ Ð˜Ð Ð Ñ Ø€N�CÐÐÑØÐ˜ÐÐÑØ%)Ð˜˜d™
Ð)Ð)Ñ)ð(ð (ð (ð (ð (ð
ð ð ð ð+ð +ñ „Xð+ð +ð +ð +ð +rL   r	   )
rX   rR   Úhuggingface_hub.dataclassesr   Úconfiguration_utilsr   Úutilsr   r	   Ú__all__rC   rL   rK   ú<module>rg      s´   ðð !Ð  à €€€à .Ð .Ð .Ð .Ð .Ð .à 3Ð 3Ð 3Ð 3Ð 3Ð 3Ø #Ð #Ð #Ð #Ð #Ð #ð €Ð>Ð?Ñ?Ô?Øðh+ð h+ð h+ð h+ð h+Ð*ñ h+ô h+ñ „ñ @Ô?ðh+ðV !Ð
!€€€rL   