§
    9²¸jJ%  ã                   ó\  — d Z ddlZddlZddlmZ ddlmZ ddlmZ ddl	m
Z
 ddlmZ dd	lmZ dd
lmZ ddlmZmZmZmZmZmZmZmZmZmZmZ ddlmZ  G d„ de
¦  «        Z G d„ de¦  «        Z  G d„ dej!        ¦  «        Z" G d„ dej!        ¦  «        Z# G d„ de¦  «        Z$ G d„ de¦  «        Z% G d„ de¦  «        Z& G d„ de¦  «        Z' G d„ d ee¦  «        Z(eZ) G d!„ d"e(e¦  «        Z* G d#„ d$e(e¦  «        Z+ G d%„ d&e¦  «        Z, G d'„ d(e¦  «        Z- G d)„ d*e¦  «        Z.g d+¢Z/dS ),zPyTorch Data2VecText model.é    N)Únné   )Úinitialization)ÚACT2FN)ÚGradientCheckpointingLayer)ÚWav2Vec2BaseModelOutput)ÚPreTrainedModel)ÚOutputRecorderé   )ÚWav2Vec2AdapterÚWav2Vec2EncoderÚWav2Vec2FeatureEncoderÚWav2Vec2FeatureProjectionÚ#Wav2Vec2ForAudioFrameClassificationÚWav2Vec2ForCTCÚ!Wav2Vec2ForSequenceClassificationÚWav2Vec2ForXVectorÚWav2Vec2ModelÚWav2Vec2PreTrainedModelÚWav2Vec2SamePadLayeré   )ÚData2VecAudioConfigc                   ó&   ‡ — e Zd Zdˆ fd„	Zd„ Zˆ xZS )ÚData2VecAudioConvLayerr   c                 óš  •— t          ¦   «                              ¦   «          |dk    r|j        |dz
           nd| _        |j        |         | _        t          j        | j        | j        |j        |         |j        |         |j	        ¬¦  «        | _
        t          j        | j        d¬¦  «        | _        t          |j                 | _        d S )Nr   r   )Úkernel_sizeÚstrideÚbiasT©Úelementwise_affine)ÚsuperÚ__init__Úconv_dimÚin_conv_dimÚout_conv_dimr   ÚConv1dÚconv_kernelÚconv_strideÚ	conv_biasÚconvÚ	LayerNormÚ
layer_normr   Úfeat_extract_activationÚ
activation)ÚselfÚconfigÚlayer_idÚ	__class__s      €úƒ/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/data2vec/modular_data2vec_audio.pyr"   zData2VecAudioConvLayer.__init__,   s¶   ø€ Ý‰Œ×ÒÑÔÐØ<DÀqºL¸L˜6œ?¨8°a©<Ô8Ð8ÈaˆÔØ"œO¨HÔ5ˆÔå”IØÔØÔØÔ*¨8Ô4ØÔ% hÔ/ØÔ!ð
ñ 
ô 
ˆŒ	õ œ, tÔ'8ÈTÐRÑRÔRˆŒÝ  Ô!?Ô@ˆŒˆˆó    c                 óÜ   — |                       |¦  «        }|                     dd¦  «        }|                      |¦  «        }|                     dd¦  «        }|                      |¦  «        }|S )Néþÿÿÿéÿÿÿÿ)r*   Ú	transposer,   r.   ©r/   Úhidden_statess     r3   ÚforwardzData2VecAudioConvLayer.forward;   se   € ØŸ	š	 -Ñ0Ô0ˆà%×/Ò/°°BÑ7Ô7ˆØŸš¨Ñ6Ô6ˆØ%×/Ò/°°BÑ7Ô7ˆàŸš¨Ñ6Ô6ˆØÐr4   )r   ©Ú__name__Ú
__module__Ú__qualname__r"   r;   Ú__classcell__©r2   s   @r3   r   r   +   sR   ø€ € € € € ðAð Að Að Að Að Aðð ð ð ð ð ð r4   r   c                   ó   — e Zd ZdS )ÚData2VecAudioPadLayerN©r=   r>   r?   © r4   r3   rC   rC   F   ó   € € € € € Ø€Dr4   rC   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )Ú Data2VecAudioPositionalConvLayerc                 ó\  •— t          ¦   «                              ¦   «          t          j        |j        |j        |j        |j        dz  |j        ¬¦  «        | _        t          |j        ¦  «        | _	        t          |j                 | _        t          j        |j        d¬¦  «        | _        d S )Nr   )r   ÚpaddingÚgroupsFr   )r!   r"   r   r&   Úhidden_sizeÚconv_pos_kernel_sizeÚnum_conv_pos_embedding_groupsr*   rC   rJ   r   r-   r.   r+   r,   ©r/   r0   r2   s     €r3   r"   z)Data2VecAudioPositionalConvLayer.__init__K   s”   ø€ Ý‰Œ×ÒÑÔÐÝ”IØÔØÔØÔ3ØÔ/°1Ñ4ØÔ7ð
ñ 
ô 
ˆŒ	õ -¨VÔ-HÑIÔIˆŒÝ  Ô!?Ô@ˆŒåœ, vÔ'9ÈeÐTÑTÔTˆŒˆˆr4   c                 ó  — |                       |¦  «        }|                      |¦  «        }|                     dd¦  «        }|                      |¦  «        }|                     dd¦  «        }|                      |¦  «        }|S ©Nr   r   )r*   rJ   r8   r,   r.   r9   s     r3   r;   z(Data2VecAudioPositionalConvLayer.forwardZ   sv   € ØŸ	š	 -Ñ0Ô0ˆØŸš ]Ñ3Ô3ˆà%×/Ò/°°1Ñ5Ô5ˆØŸš¨Ñ6Ô6ˆØ%×/Ò/°°1Ñ5Ô5ˆØŸš¨Ñ6Ô6ˆØÐr4   r<   rA   s   @r3   rH   rH   J   sL   ø€ € € € € ðUð Uð Uð Uð Uðð ð ð ð ð ð r4   rH   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )Ú$Data2VecAudioPositionalConvEmbeddingc                 ó¸   •‡— t          ¦   «                              ¦   «          t          j        ˆfd„t	          ‰j        ¦  «        D ¦   «         ¦  «        | _        d S )Nc                 ó.   •— g | ]}t          ‰¦  «        ‘ŒS rE   )rH   )Ú.0Ú_r0   s     €r3   ú
<listcomp>zAData2VecAudioPositionalConvEmbedding.__init__.<locals>.<listcomp>i   s"   ø€ ÐeÐeÐe¸!Õ-¨fÑ5Ô5ÐeÐeÐer4   )r!   r"   r   Ú
ModuleListÚrangeÚnum_conv_pos_embeddingsÚlayersrO   s    `€r3   r"   z-Data2VecAudioPositionalConvEmbedding.__init__f   sS   øø€ Ý‰Œ×ÒÑÔÐÝ”mØeÐeÐeÐe½uÀVÔEcÑ?dÔ?dÐeÑeÔeñ
ô 
ˆŒˆˆr4   c                 óˆ   — |                      dd¦  «        }| j        D ]} ||¦  «        }Œ|                      dd¦  «        }|S rQ   )r8   r\   )r/   r:   Úlayers      r3   r;   z,Data2VecAudioPositionalConvEmbedding.forwardl   sT   € Ø%×/Ò/°°1Ñ5Ô5ˆØ”[ð 	1ð 	1ˆEØ!˜E -Ñ0Ô0ˆMˆMØ%×/Ò/°°1Ñ5Ô5ˆØÐr4   r<   rA   s   @r3   rS   rS   e   sG   ø€ € € € € ð
ð 
ð 
ð 
ð 
ðð ð ð ð ð ð r4   rS   c                   ó   — e Zd Zd„ ZdS )ÚData2VecAudioFeatureEncoderc                 óÐ   ‡— t           j                             | ¦  «         t          j        ˆfd„t	          ‰j        ¦  «        D ¦   «         ¦  «        | _        d| _        d| _        d S )Nc                 ó2   •— g | ]}t          ‰|¬ ¦  «        ‘ŒS ))r1   )r   )rV   Úir0   s     €r3   rX   z8Data2VecAudioFeatureEncoder.__init__.<locals>.<listcomp>x   s'   ø€ ÐgÐgÐg¸AÕ# F°QÐ7Ñ7Ô7ÐgÐgÐgr4   FT)	r   ÚModuler"   rY   rZ   Únum_feat_extract_layersÚconv_layersÚgradient_checkpointingÚ_requires_grad©r/   r0   s    `r3   r"   z$Data2VecAudioFeatureEncoder.__init__u   sg   ø€ Ý
Œ	×Ò˜4Ñ Ô Ð Ýœ=ØgÐgÐgÐgÅÀvÔGeÑAfÔAfÐgÑgÔgñ
ô 
ˆÔð ',ˆÔ#Ø"ˆÔÐÐr4   N)r=   r>   r?   r"   rE   r4   r3   r`   r`   t   s#   € € € € € ð#ð #ð #ð #ð #r4   r`   c                   ó   — e Zd ZdS )ÚData2VecAudioFeatureProjectionNrD   rE   r4   r3   rk   rk   ~   rF   r4   rk   c                   ó   — e Zd ZdS )ÚData2VecAudioEncoderNrD   rE   r4   r3   rm   rm   ‚   rF   r4   rm   c                   ó   — e Zd ZdS )ÚData2VecAudioAdapterNrD   rE   r4   r3   ro   ro   †   rF   r4   ro   c                   óš   — e Zd ZU eed<   dZdZdZdZdZ	dZ
dZe eedd¬¦  «        d	œZ ej        ¦   «         d
„ ¦   «         Zd„ Zd„ Zd„ ZdS )ÚData2VecAudioPreTrainedModelr0   Údata2vec_audioÚinput_valuesÚaudioTr   Úencoder)ÚindexÚ
layer_name)r:   Ú
attentionsc                 ó¨  — t          j        | |¦  «         t          |t          ¦  «        rgt	          j        d|j        j        z  ¦  «        }t          j	        |j        j
        | |¬¦  «         t          j	        |j        j        | |¬¦  «         dS t          |t          ¦  «        r!t          j        |j        j        d¦  «         dS t          |t          j        ¦  «        rnt          j        |j
        ¦  «         |j        �Pt	          j        |j        |j        |j        d         z  z  ¦  «        }t          j	        |j        | |¬¦  «         dS dS dS )zInitialize the weightsr   )ÚaÚbr   N)r	   Ú_init_weightsÚ
isinstancerk   ÚmathÚsqrtÚ
projectionÚin_featuresÚinitÚuniform_Úweightr   rH   Ú	constant_r*   r   r&   Úkaiming_normal_rK   Úin_channelsr   )r/   ÚmoduleÚks      r3   r|   z*Data2VecAudioPreTrainedModel._init_weights˜   sA  € õ 	Ô% d¨FÑ3Ô3Ð3Ý�fÕ<Ñ=Ô=ð 	6Ý”	˜!˜fÔ/Ô;Ñ;Ñ<Ô<ˆAÝŒM˜&Ô+Ô2°q°b¸AÐ>Ñ>Ô>Ð>ÝŒM˜&Ô+Ô0°Q°B¸!Ð<Ñ<Ô<Ð<Ð<Ð<Ý˜Õ @ÑAÔAð 	6ÝŒN˜6œ;Ô+¨QÑ/Ô/Ð/Ð/Ð/Ý˜¥¤	Ñ*Ô*ð 	6ÝÔ  ¤Ñ/Ô/Ð/àŒ{Ð&Ý”I˜fœm¨vÔ/AÀFÔDVÐWXÔDYÑ/YÑZÑ[Ô[�Ý”˜fœk¨a¨R°1Ð5Ñ5Ô5Ð5Ð5Ð5ð	6ð 	6ð 'Ð&r4   c                 ó    — t          d¦  «        ‚©NzNot needed for Data2VecAudio©ÚAttributeError©r/   s    r3   Ú_get_adaptersz*Data2VecAudioPreTrainedModel._get_adapters©   ó   € ÝÐ;Ñ<Ô<Ð<r4   c                 ó    — t          d¦  «        ‚r‹   rŒ   rŽ   s    r3   Úinit_adapter_layersz0Data2VecAudioPreTrainedModel.init_adapter_layers¬   r�   r4   c                 ó    — t          d¦  «        ‚r‹   rŒ   rŽ   s    r3   Úload_adapterz)Data2VecAudioPreTrainedModel.load_adapter¯   r�   r4   N)r=   r>   r?   r   Ú__annotations__Úbase_model_prefixÚmain_input_nameÚinput_modalitiesÚsupports_gradient_checkpointingÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnÚData2VecAudioEncoderLayerr
   ÚData2VecAudioAttentionÚ_can_record_outputsÚtorchÚno_gradr|   r�   r’   r”   rE   r4   r3   rq   rq   Š   sÀ   € € € € € € ØÐÐÑØ(ÐØ$€OØÐØ&*Ð#ØÐØ€NØÐà2Ø$�nÐ%;À1ÐQZÐ[Ñ[Ô[ðð Ðð
 €U„]�_„_ð6ð 6ñ „_ð6ð =ð =ð =ð=ð =ð =ð=ð =ð =ð =ð =r4   rq   c                   ó0   ‡ — e Zd Zdefd„Zd„ Zˆ fd„Zˆ xZS )ÚData2VecAudioModelr0   c                 óÔ  — t                                | |¦  «         || _        t          |¦  «        | _        t          |¦  «        | _        |j        dk    s|j        dk    rBt          j
        t          j        |j        ¦  «                             ¦   «         ¦  «        | _        t!          |¦  «        | _        |j        rt'          |¦  «        nd | _        |                      ¦   «          d S )Ng        )rq   r"   r0   r`   Úfeature_extractorrk   Úfeature_projectionÚmask_time_probÚmask_feature_probr   Ú	Parameterr    ÚTensorrL   rƒ   Úmasked_spec_embedrm   ru   Úadd_adapterro   ÚadapterÚ	post_initri   s     r3   r"   zData2VecAudioModel.__init__·   sË   € Ý$×-Ò-¨d°FÑ;Ô;Ð;ØˆŒÝ!<¸VÑ!DÔ!DˆÔÝ"@ÀÑ"HÔ"HˆÔð Ô  3Ò&Ð&¨&Ô*BÀSÒ*HÐ*HÝ%'¤\µ%´,¸vÔ?QÑ2RÔ2R×2[Ò2[Ñ2]Ô2]Ñ%^Ô%^ˆDÔ"å+¨FÑ3Ô3ˆŒà7=Ô7IÐSÕ+¨FÑ3Ô3Ð3ÈtˆŒð 	�ŠÑÔÐÐÐr4   c                 ó8   — | j                              ¦   «          dS )z¨
        Calling this function will disable the gradient computation for the feature encoder so that its parameter will
        not be updated during training.
        N)r¥   Ú_freeze_parametersrŽ   s    r3   Úfreeze_feature_encoderz)Data2VecAudioModel.freeze_feature_encoderÈ   s   € ð
 	Ô×1Ò1Ñ3Ô3Ð3Ð3Ð3r4   c                 ó6   •—  t          ¦   «         j        di |¤ŽS ©NrE   ©r!   r;   ©r/   Úsuper_kwargsr2   s     €r3   r;   zData2VecAudioModel.forwardÏ   ó   ø€ Ø�u‰wŒwŒÐ.Ð. Ð.Ð.Ð.r4   )r=   r>   r?   r   r"   r±   r;   r@   rA   s   @r3   r£   r£   ¶   sc   ø€ € € € € ðÐ2ð ð ð ð ð"4ð 4ð 4ð/ð /ð /ð /ð /ð /ð /ð /ð /r4   r£   c                   ó0   ‡ — e Zd Zd„ Zd„ Zd„ Zˆ fd„Zˆ xZS )ÚData2VecAudioForCTCc                 óŽ  — t                                | |¦  «         t          |¦  «        | _        t	          j        |j        ¦  «        | _        |j        €t          d| j
        › d�¦  «        ‚t          |d¦  «        r|j        r|j        n|j        }t	          j        ||j        ¦  «        | _        |                      ¦   «          dS )aZ  
        config ([`Data2VecAudioForCTC`]):
            Model configuration class with all the parameters of the model. Initializing with a config file does not
            load the weights associated with the model, only the configuration. Check out the
            [`~PreTrainedModel.from_pretrained`]  method to load the model weights.
        NzYou are trying to instantiate zü with a configuration that does not define the vocabulary size of the language model head. Please instantiate the model as follows: `Data2VecAudioForCTC.from_pretrained(..., vocab_size=vocab_size)`. or define `vocab_size` of your model's configuration.r¬   )rq   r"   r£   rr   r   ÚDropoutÚfinal_dropoutÚdropoutÚ
vocab_sizeÚ
ValueErrorr2   Úhasattrr¬   Úoutput_hidden_sizerL   ÚLinearÚlm_headr®   )r/   r0   rÁ   s      r3   r"   zData2VecAudioForCTC.__init__Ô   sÓ   € õ 	%×-Ò-¨d°FÑ;Ô;Ð;å0°Ñ8Ô8ˆÔÝ”z &Ô"6Ñ7Ô7ˆŒàÔÐ$ÝðH°´ð Hð Hð Hñô ð õ *1°¸Ñ)GÔ)GÐvÈFÔL^ÐvˆFÔ%Ð%ÐdjÔdvð 	õ ”yÐ!3°VÔ5FÑGÔGˆŒð 	�ŠÑÔÐÐÐr4   c                 ó    — t          d¦  «        ‚r‹   rŒ   rŽ   s    r3   Úfreeze_base_modelz%Data2VecAudioForCTC.freeze_base_modelï   r�   r4   c                 ó    — t          d¦  «        ‚r‹   rŒ   rŽ   s    r3   Útie_weightszData2VecAudioForCTC.tie_weightsò   r�   r4   c                 ó6   •—  t          ¦   «         j        di |¤ŽS r³   r´   rµ   s     €r3   r;   zData2VecAudioForCTC.forwardõ   r·   r4   )r=   r>   r?   r"   rÅ   rÇ   r;   r@   rA   s   @r3   r¹   r¹   Ó   se   ø€ € € € € ðð ð ð6=ð =ð =ð=ð =ð =ð/ð /ð /ð /ð /ð /ð /ð /ð /r4   r¹   c                   ó   — e Zd ZdS )Ú&Data2VecAudioForSequenceClassificationNrD   rE   r4   r3   rÊ   rÊ   ù   rF   r4   rÊ   c                   ó   — e Zd ZdS )Ú(Data2VecAudioForAudioFrameClassificationNrD   rE   r4   r3   rÌ   rÌ   ý   rF   r4   rÌ   c                   ó   — e Zd ZdS )ÚData2VecAudioForXVectorNrD   rE   r4   r3   rÎ   rÎ     rF   r4   rÎ   )rÌ   r¹   rÊ   rÎ   r£   rq   )0Ú__doc__r~   r    r   Ú r   r‚   Úactivationsr   Úmodeling_layersr   Úmodeling_outputsr   Úmodeling_utilsr	   Úutils.output_capturingr
   Úwav2vec2.modeling_wav2vec2r   r   r   r   r   r   r   r   r   r   r   Úconfiguration_data2vec_audior   r   rC   rd   rH   rS   r`   rk   rm   ro   rq   ÚData2VecAudioBaseModelOutputr£   r¹   rÊ   rÌ   rÎ   Ú__all__rE   r4   r3   ú<module>rÚ      s²  ðð "Ð !à €€€à €€€Ø Ð Ð Ð Ð Ð à &Ð &Ð &Ð &Ð &Ð &Ø !Ð !Ð !Ð !Ð !Ð !Ø 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø 7Ð 7Ð 7Ð 7Ð 7Ð 7Ø -Ð -Ð -Ð -Ð -Ð -Ø 4Ð 4Ð 4Ð 4Ð 4Ð 4ðð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð >Ð =Ð =Ð =Ð =Ð =ðð ð ð ð Ð7ñ ô ð ð6	ð 	ð 	ð 	ð 	Ð0ñ 	ô 	ð 	ðð ð ð ð  r¤yñ ô ð ð6ð ð ð ð ¨2¬9ñ ô ð ð#ð #ð #ð #ð #Ð"8ñ #ô #ð #ð	ð 	ð 	ð 	ð 	Ð%>ñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	˜?ñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	˜?ñ 	ô 	ð 	ð&=ð &=ð &=ð &=ð &= ?Ð4Kñ &=ô &=ð &=ðR  7Ð ð/ð /ð /ð /ð /Ð5°}ñ /ô /ð /ð:#/ð #/ð #/ð #/ð #/Ð6¸ñ #/ô #/ð #/ðL	ð 	ð 	ð 	ð 	Ð-Nñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð/Rñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð0ñ 	ô 	ð 	ðð ð €€€r4   