§
    9²¸j§Ë  ã                   ó>  — d dl Z d dlZd dlm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 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! ddl"m#Z#m$Z$ ddl%m&Z& ddl'm(Z(m)Z)m*Z* ddl+m,Z,m-Z- ddl.m/Z/m0Z0 ddl1m2Z2  G d„ de¦  «        Z3 G d„ dej4        ¦  «        Z5 G d„ dej4        ¦  «        Z6 G d„ dej4        ¦  «        Z7 G d„ dej4        ¦  «        Z8 G d „ d!ej4        ¦  «        Z9	 	 dSd#ej4        d$ej:        d%ej:        d&ej:        d'ej:        dz  d(e;dz  d)e;d*e&e(         fd+„Z< G d,„ d-ej4        ¦  «        Z= G d.„ d/ej4        ¦  «        Z> G d0„ d1e¦  «        Z? G d2„ d3ej4        ¦  «        Z@ G d4„ d5ej4        ¦  «        ZA G d6„ d7ej4        ¦  «        ZBe) G d8„ d9e$¦  «        ¦   «         ZC	 	 dTd:eDeEeEf         d;e;d<eEd'ejF        dz  d=eEd>ejG        fd?„ZHe ZIe) G d@„ dAeC¦  «        ¦   «         ZJ e)dB¬C¦  «         G dD„ dEeC¦  «        ¦   «         ZK e)dF¬C¦  «         G dG„ dHeC¦  «        ¦   «         ZLe) G dI„ dJeC¦  «        ¦   «         ZM G dK„ dLej4        ¦  «        ZN G dM„ dNej4        ¦  «        ZO e)dO¬C¦  «         G dP„ dQeC¦  «        ¦   «         ZPg dR¢ZQdS )Ué    N)ÚCallable)Únn)ÚCrossEntropyLossé   )Úinitialization)ÚACT2FN)Úfilter_output_hidden_states)Úis_deepspeed_zero3_enabled)Úis_fsdp_managed_module)Úcreate_bidirectional_mask)ÚFlashAttentionKwargs)ÚGradientCheckpointingLayer)ÚBaseModelOutputÚCausalLMOutputÚSequenceClassifierOutputÚTokenClassifierOutputÚWav2Vec2BaseModelOutputÚXVectorOutput)ÚALL_ATTENTION_FUNCTIONSÚPreTrainedModel)ÚUnpack)ÚTransformersKwargsÚauto_docstringÚis_peft_available)Úcan_return_tupleÚmerge_with_config_defaults)ÚOutputRecorderÚcapture_outputsé   )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      €ú„/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/data2vec/modeling_data2vec_audio.pyr*   zData2VecAudioConvLayer.__init__7   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)r2   Ú	transposer4   r6   ©r8   Úhidden_statess     r<   ÚforwardzData2VecAudioConvLayer.forwardF   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r=   ©r   ©Ú__name__Ú
__module__Ú__qualname__r*   rD   Ú__classcell__©r;   s   @r<   r"   r"   6   sR   ø€ € € € € ðAð Að Að Að Að Aðð ð ð ð ð ð r=   r"   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚData2VecAudioPadLayerc                 ól   •— t          ¦   «                              ¦   «          |dz  dk    rdnd| _        d S )Né   r   r   )r)   r*   Únum_pad_remove)r8   Únum_conv_pos_embeddingsr;   s     €r<   r*   zData2VecAudioPadLayer.__init__R   s:   ø€ Ý‰Œ×ÒÑÔÐØ#:¸QÑ#>À!Ò#CÐ#C˜a˜aÈˆÔÐÐr=   c                 óJ   — | j         dk    r|d d …d d …d | j          …f         }|S ©Nr   )rP   rB   s     r<   rD   zData2VecAudioPadLayer.forwardV   s;   € ØÔ Ò"Ð"Ø)¨!¨!¨!¨Q¨Q¨QÐ0F°4Ô3FÐ2FÐ0FÐ*FÔGˆMØÐr=   rF   rK   s   @r<   rM   rM   Q   sL   ø€ € € € € ðKð Kð Kð Kð Kðð ð ð ð ð ð r=   rM   c                   ó$   ‡ — 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 )NrO   )r$   ÚpaddingÚgroupsFr'   )r)   r*   r   r.   Úhidden_sizeÚconv_pos_kernel_sizeÚnum_conv_pos_embedding_groupsr2   rM   rW   r   r5   r6   r3   r4   ©r8   r9   r;   s     €r<   r*   z)Data2VecAudioPositionalConvLayer.__init__]   s”   ø€ Ý‰Œ×ÒÑÔÐÝ”IØÔØÔØÔ3ØÔ/°1Ñ4ØÔ7ð
ñ 
ô 
ˆŒ	õ -¨VÔ-HÑIÔIˆŒÝ  Ô!?Ô@ˆŒåœ, vÔ'9ÈeÐTÑTÔTˆŒˆˆr=   c                 ó  — |                       |¦  «        }|                      |¦  «        }|                     dd¦  «        }|                      |¦  «        }|                     dd¦  «        }|                      |¦  «        }|S ©Nr   rO   )r2   rW   rA   r4   r6   rB   s     r<   rD   z(Data2VecAudioPositionalConvLayer.forwardl   sv   € ØŸ	š	 -Ñ0Ô0ˆØŸš ]Ñ3Ô3ˆà%×/Ò/°°1Ñ5Ô5ˆØŸš¨Ñ6Ô6ˆØ%×/Ò/°°1Ñ5Ô5ˆØŸš¨Ñ6Ô6ˆØÐr=   rF   rK   s   @r<   rU   rU   \   sL   ø€ € € € € ðUð Uð Uð Uð Uðð ð ð ð ð ð r=   rU   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )Ú$Data2VecAudioPositionalConvEmbeddingc                 ó¸   •‡— t          ¦   «                              ¦   «          t          j        ˆfd„t	          ‰j        ¦  «        D ¦   «         ¦  «        | _        d S )Nc                 ó.   •— g | ]}t          ‰¦  «        ‘ŒS © )rU   ©Ú.0Ú_r9   s     €r<   ú
<listcomp>zAData2VecAudioPositionalConvEmbedding.__init__.<locals>.<listcomp>{   s"   ø€ ÐeÐeÐe¸!Õ-¨fÑ5Ô5ÐeÐeÐer=   )r)   r*   r   Ú
ModuleListÚrangerQ   Úlayersr\   s    `€r<   r*   z-Data2VecAudioPositionalConvEmbedding.__init__x   sS   øø€ Ý‰Œ×ÒÑÔÐÝ”mØeÐeÐeÐe½uÀVÔEcÑ?dÔ?dÐeÑeÔeñ
ô 
ˆŒˆˆr=   c                 óˆ   — |                      dd¦  «        }| j        D ]} ||¦  «        }Œ|                      dd¦  «        }|S r^   )rA   rj   )r8   rC   Úlayers      r<   rD   z,Data2VecAudioPositionalConvEmbedding.forward~   sT   € Ø%×/Ò/°°1Ñ5Ô5ˆØ”[ð 	1ð 	1ˆEØ!˜E -Ñ0Ô0ˆMˆMØ%×/Ò/°°1Ñ5Ô5ˆØÐr=   rF   rK   s   @r<   r`   r`   w   sG   ø€ € € € € ð
ð 
ð 
ð 
ð 
ðð ð ð ð ð ð r=   r`   c                   ó.   ‡ — e Zd ZdZˆ fd„Zd„ Zd„ Zˆ xZS )ÚData2VecAudioFeatureEncoderz.Construct the features from raw audio waveformc                 óÔ   •‡— t          ¦   «                              ¦   «          t          j        ˆfd„t	          ‰j        ¦  «        D ¦   «         ¦  «        | _        d| _        d| _        d S )Nc                 ó2   •— g | ]}t          ‰|¬ ¦  «        ‘ŒS ))r:   )r"   ©re   Úir9   s     €r<   rg   z8Data2VecAudioFeatureEncoder.__init__.<locals>.<listcomp>Œ   s'   ø€ ÐgÐgÐg¸AÕ# F°QÐ7Ñ7Ô7ÐgÐgÐgr=   FT)	r)   r*   r   rh   ri   Únum_feat_extract_layersÚconv_layersÚgradient_checkpointingÚ_requires_gradr\   s    `€r<   r*   z$Data2VecAudioFeatureEncoder.__init__‰   sh   øø€ Ý‰Œ×ÒÑÔÐÝœ=ØgÐgÐgÐgÅÀvÔGeÑAfÔAfÐgÑgÔgñ
ô 
ˆÔð ',ˆÔ#Ø"ˆÔÐÐr=   c                 óP   — |                       ¦   «         D ]	}d|_        Œ
d| _        d S )NF)Ú
parametersÚrequires_gradrv   ©r8   Úparams     r<   Ú_freeze_parametersz.Data2VecAudioFeatureEncoder._freeze_parameters‘   s4   € Ø—_’_Ñ&Ô&ð 	(ð 	(ˆEØ"'ˆEÔÐØ#ˆÔÐÐr=   c                 ór   — |d d …d f         }| j         r| j        rd|_        | j        D ]} ||¦  «        }Œ|S )NT)rv   Útrainingry   rt   )r8   Úinput_valuesrC   Ú
conv_layers       r<   rD   z#Data2VecAudioFeatureEncoder.forward–   s[   € Ø$ Q Q Q¨ WÔ-ˆð Ôð 	/ 4¤=ð 	/Ø*.ˆMÔ'àÔ*ð 	6ð 	6ˆJØ&˜J }Ñ5Ô5ˆMˆMàÐr=   )rG   rH   rI   Ú__doc__r*   r|   rD   rJ   rK   s   @r<   rn   rn   †   s\   ø€ € € € € Ø8Ð8ð#ð #ð #ð #ð #ð$ð $ð $ð

ð 
ð 
ð 
ð 
ð 
ð 
r=   rn   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚData2VecAudioFeatureProjectionc                 ó.  •— t          ¦   «                              ¦   «          t          j        |j        d         |j        ¬¦  «        | _        t          j        |j        d         |j        ¦  «        | _	        t          j
        |j        ¦  «        | _        d S )Nr@   ©Úeps)r)   r*   r   r3   r+   Úlayer_norm_epsr4   ÚLinearrY   Ú
projectionÚDropoutÚfeat_proj_dropoutÚdropoutr\   s     €r<   r*   z'Data2VecAudioFeatureProjection.__init__¤   sn   ø€ Ý‰Œ×ÒÑÔÐÝœ, v¤°rÔ':ÀÔ@UÐVÑVÔVˆŒÝœ) F¤O°BÔ$7¸Ô9KÑLÔLˆŒÝ”z &Ô":Ñ;Ô;ˆŒˆˆr=   c                 óˆ   — |                       |¦  «        }|                      |¦  «        }|                      |¦  «        }||fS ©N)r4   r‰   rŒ   )r8   rC   Únorm_hidden_statess      r<   rD   z&Data2VecAudioFeatureProjection.forwardª   sC   € à!Ÿ_š_¨]Ñ;Ô;ÐØŸšÐ(:Ñ;Ô;ˆØŸš ]Ñ3Ô3ˆØÐ0Ð0Ð0r=   rF   rK   s   @r<   rƒ   rƒ   £   sG   ø€ € € € € ð<ð <ð <ð <ð <ð1ð 1ð 1ð 1ð 1ð 1ð 1r=   rƒ   ç        ÚmoduleÚqueryÚkeyÚvalueÚattention_maskÚscalingrŒ   Úkwargsc                 ó®  — |€|                      d¦  «        dz  }t          j        ||                     dd¦  «        ¦  «        |z  }|�||z   }t          j                             |d¬¦  «        }t          j                             ||| j        ¬¦  «        }t          j        ||¦  «        }	|	                     dd¦  «         	                    ¦   «         }	|	|fS )Nr@   ç      à¿rO   r   ©Údim)Úpr~   r   )
ÚsizeÚtorchÚmatmulrA   r   Ú
functionalÚsoftmaxrŒ   r~   Ú
contiguous)
r‘   r’   r“   r”   r•   r–   rŒ   r—   Úattn_weightsÚattn_outputs
             r<   Úeager_attention_forwardr¥   ²   sÈ   € ð €Ø—*’*˜R‘.”. DÑ(ˆõ ”<  s§}¢}°Q¸Ñ':Ô':Ñ;Ô;¸gÑE€LàÐ!Ø# nÑ4ˆå”=×(Ò(¨¸2Ð(Ñ>Ô>€LÝ”=×(Ò(¨¸È6Ì?Ð(Ñ[Ô[€Lå”,˜|¨UÑ3Ô3€KØ×'Ò'¨¨1Ñ-Ô-×8Ò8Ñ:Ô:€Kà˜Ð$Ð$r=   c                   óà   ‡ — e Zd ZdZ	 	 	 	 	 ddededed	ed
edededz  fˆ fd„Z	 	 	 dde	j
        de	j
        dz  de	j
        dz  dedz  dee         dee	j
        e	j
        dz  f         fd„Zˆ xZS )ÚData2VecAudioAttentionz=Multi-headed attention from 'Attention Is All You Need' paperr�   FTNÚ	embed_dimÚ	num_headsrŒ   Ú
is_decoderr&   Ú	is_causalr9   c                 ó
  •— t          ¦   «                              ¦   «          || _        || _        || _        ||z  | _        || _        | j        |z  | j        k    rt          d| j        › d|› d�¦  «        ‚| j        dz  | _        || _	        || _
        t          j        |||¬¦  «        | _        t          j        |||¬¦  «        | _        t          j        |||¬¦  «        | _        t          j        |||¬¦  «        | _        d S )Nz;embed_dim must be divisible by num_heads (got `embed_dim`: z and `num_heads`: z).r™   )r&   )r)   r*   r¨   r©   rŒ   Úhead_dimr9   Ú
ValueErrorr–   rª   r«   r   rˆ   Úk_projÚv_projÚq_projÚout_proj)	r8   r¨   r©   rŒ   rª   r&   r«   r9   r;   s	           €r<   r*   zData2VecAudioAttention.__init__Ñ   s  ø€ õ 	‰Œ×ÒÑÔÐØ"ˆŒØ"ˆŒØˆŒØ! YÑ.ˆŒØˆŒàŒM˜IÑ%¨$¬.Ò8Ð8Ýð3ÈdÌnð 3ð 3Ø%.ð3ð 3ð 3ñô ð ð ”} dÑ*ˆŒØ$ˆŒØ"ˆŒå”i 	¨9¸4Ð@Ñ@Ô@ˆŒÝ”i 	¨9¸4Ð@Ñ@Ô@ˆŒÝ”i 	¨9¸4Ð@Ñ@Ô@ˆŒÝœ	 )¨Y¸TÐBÑBÔBˆŒˆˆr=   rC   Úkey_value_statesr•   Úoutput_attentionsr—   Úreturnc                 óø  — |du}|j         dd…         }g |¢d‘| j        ‘R }|                      |¦  «                             |¦  «                             dd¦  «        }	|r|n|}
g |
j         dd…         ¢d‘| j        ‘R }|                      |
¦  «                             |¦  «                             dd¦  «        }|                      |
¦  «                             |¦  «                             dd¦  «        }t          j        | j	        j
        t          ¦  «        } || |	|||f| j        sdn| j        | j        |dœ|¤Ž\  }} |j        g |¢d‘R Ž                      ¦   «         }|                      |¦  «        }||fS )z#Input shape: Batch x Time x ChannelNr@   r   rO   r�   )rŒ   r–   r´   )Úshaper­   r±   ÚviewrA   r¯   r°   r   Úget_interfacer9   Ú_attn_implementationr¥   r~   rŒ   r–   Úreshaper¢   r²   )r8   rC   r³   r•   r´   r—   Úis_cross_attentionÚinput_shapeÚhidden_shapeÚquery_statesÚcurrent_statesÚkv_shapeÚ
key_statesÚvalue_statesÚattention_interfacer¤   r£   s                    r<   rD   zData2VecAudioAttention.forwardð   s»  € ð .°TÐ9Ðð $Ô)¨#¨2¨#Ô.ˆà8˜Ð8 bÐ8¨$¬-Ð8Ð8ˆð —{’{ =Ñ1Ô1×6Ò6°|ÑDÔD×NÒNÈqÐRSÑTÔTˆà-?ÐRÐ)Ð)À]ˆØB�^Ô)¨#¨2¨#Ô.ÐB°ÐB°D´MÐBÐBˆØ—[’[ Ñ0Ô0×5Ò5°hÑ?Ô?×IÒIÈ!ÈQÑOÔOˆ
Ø—{’{ >Ñ2Ô2×7Ò7¸ÑAÔA×KÒKÈAÈqÑQÔQˆå(?Ô(MØŒKÔ,Õ.Eñ)
ô )
Ðð %8Ð$7ØØØØØð
%
ð  $œ}Ð>�C�C°$´,Ø”LØ/ð
%
ð 
%
ð ð
%
ð 
%
Ñ!ˆ�\ð *�kÔ)Ð;¨;Ð;¸Ð;Ð;Ð;×FÒFÑHÔHˆØ—m’m KÑ0Ô0ˆà˜LÐ(Ð(r=   )r�   FTFN)NNF)rG   rH   rI   r�   ÚintÚfloatÚboolr    r*   rž   ÚTensorr   r   ÚtuplerD   rJ   rK   s   @r<   r§   r§   Î   s<  ø€ € € € € ØGÐGð Ø ØØØ-1ðCð CàðCð ðCð ð	Cð
 ðCð ðCð ðCð $ dÑ*ðCð Cð Cð Cð Cð CðD 15Ø.2Ø).ð0)ð 0)à”|ð0)ð  œ,¨Ñ-ð0)ð œ tÑ+ð	0)ð
   $™;ð0)ð Ð-Ô.ð0)ð 
ˆuŒ|˜Uœ\¨DÑ0Ð0Ô	1ð0)ð 0)ð 0)ð 0)ð 0)ð 0)ð 0)ð 0)r=   r§   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚData2VecAudioFeedForwardc                 óÌ  •— t          ¦   «                              ¦   «          t          j        |j        ¦  «        | _        t          j        |j        |j        ¦  «        | _	        t          |j        t          ¦  «        rt          |j                 | _        n|j        | _        t          j        |j        |j        ¦  «        | _        t          j        |j        ¦  «        | _        d S rŽ   )r)   r*   r   rŠ   Úactivation_dropoutÚintermediate_dropoutrˆ   rY   Úintermediate_sizeÚintermediate_denseÚ
isinstanceÚ
hidden_actÚstrr   Úintermediate_act_fnÚoutput_denseÚhidden_dropoutÚoutput_dropoutr\   s     €r<   r*   z!Data2VecAudioFeedForward.__init__$  s°   ø€ Ý‰Œ×ÒÑÔÐÝ$&¤J¨vÔ/HÑ$IÔ$IˆÔ!å"$¤)¨FÔ,>ÀÔ@XÑ"YÔ"YˆÔÝ�fÔ'­Ñ-Ô-ð 	9Ý'-¨fÔ.?Ô'@ˆDÔ$Ð$à'-Ô'8ˆDÔ$åœI fÔ&>ÀÔ@RÑSÔSˆÔÝ œj¨Ô)>Ñ?Ô?ˆÔÐÐr=   c                 óØ   — |                       |¦  «        }|                      |¦  «        }|                      |¦  «        }|                      |¦  «        }|                      |¦  «        }|S rŽ   )rÐ   rÔ   rÎ   rÕ   r×   rB   s     r<   rD   z Data2VecAudioFeedForward.forward1  sg   € Ø×/Ò/°Ñ>Ô>ˆØ×0Ò0°Ñ?Ô?ˆØ×1Ò1°-Ñ@Ô@ˆà×)Ò)¨-Ñ8Ô8ˆØ×+Ò+¨MÑ:Ô:ˆØÐr=   rF   rK   s   @r<   rË   rË   #  sL   ø€ € € € € ð@ð @ð @ð @ð @ðð ð ð ð ð ð r=   rË   c                   ó\   ‡ — e Zd Zˆ fd„Z	 ddej        dej        dz  dee         fd„Zˆ xZ	S )ÚData2VecAudioEncoderLayerc                 ó�  •— t          ¦   «                              ¦   «          t          |j        |j        |j        d|¬¦  «        | _        t          j        |j	        ¦  «        | _
        t          j        |j        |j        ¬¦  «        | _        t          |¦  «        | _        t          j        |j        |j        ¬¦  «        | _        d S )NF)r¨   r©   rŒ   rª   r9   r…   )r)   r*   r§   rY   Únum_attention_headsÚattention_dropoutÚ	attentionr   rŠ   rÖ   rŒ   r3   r‡   r4   rË   Úfeed_forwardÚfinal_layer_normr\   s     €r<   r*   z"Data2VecAudioEncoderLayer.__init__<  s¬   ø€ Ý‰Œ×ÒÑÔÐÝ/ØÔ(ØÔ0ØÔ,ØØð
ñ 
ô 
ˆŒõ ”z &Ô"7Ñ8Ô8ˆŒÝœ, vÔ'9¸vÔ?TÐUÑUÔUˆŒÝ4°VÑ<Ô<ˆÔÝ "¤¨VÔ-?ÀVÔEZÐ [Ñ [Ô [ˆÔÐÐr=   NrC   r•   r—   c                 óè   — |} | j         |fd|i|¤Ž\  }}|                      |¦  «        }||z   }|                      |¦  «        }||                      |¦  «        z   }|                      |¦  «        }|S )Nr•   )rÞ   rŒ   r4   rß   rà   )r8   rC   r•   r—   Úattn_residualrf   s         r<   rD   z!Data2VecAudioEncoderLayer.forwardK  sŠ   € ð &ˆØ)˜4œ>¨-ÐaÐaÈÐaÐZ`ÐaÐaÑˆ�qØŸš ]Ñ3Ô3ˆØ%¨Ñ5ˆàŸš¨Ñ6Ô6ˆØ%¨×(9Ò(9¸-Ñ(HÔ(HÑHˆØ×-Ò-¨mÑ<Ô<ˆàÐr=   rŽ   )
rG   rH   rI   r*   rž   rÈ   r   r   rD   rJ   rK   s   @r<   rÚ   rÚ   ;  s†   ø€ € € € € ð\ð \ð \ð \ð \ð$ /3ðð à”|ðð œ tÑ+ðð Ð+Ô,ð	ð ð ð ð ð ð ð r=   rÚ   c                   ó\   ‡ — e Zd Zˆ fd„Z	 ddej        dej        dz  dee         fd„Z	ˆ xZ
S )ÚData2VecAudioEncoderc                 ó‚  •‡— t          ¦   «                              ¦   «          ‰| _        t          ‰¦  «        | _        t          j        ‰j        ‰j        ¬¦  «        | _	        t          j
        ‰j        ¦  «        | _        t          j        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        d| _        d S )Nr…   c                 ó.   •— g | ]}t          ‰¦  «        ‘ŒS rc   )rÚ   rd   s     €r<   rg   z1Data2VecAudioEncoder.__init__.<locals>.<listcomp>d  s"   ø€ Ð$pÐ$pÐ$pÈ1Õ%>¸vÑ%FÔ%FÐ$pÐ$pÐ$pr=   F)r)   r*   r9   r`   Úpos_conv_embedr   r3   rY   r‡   r4   rŠ   rÖ   rŒ   rh   ri   Únum_hidden_layersrj   ru   r\   s    `€r<   r*   zData2VecAudioEncoder.__init__^  s¢   øø€ Ý‰Œ×ÒÑÔÐØˆŒÝBÀ6ÑJÔJˆÔÝœ, vÔ'9¸vÔ?TÐUÑUÔUˆŒÝ”z &Ô"7Ñ8Ô8ˆŒÝ”mÐ$pÐ$pÐ$pÐ$pÕPUÐV\ÔVnÑPoÔPoÐ$pÑ$pÔ$pÑqÔqˆŒØ&+ˆÔ#Ð#Ð#r=   NrC   r•   r—   c                 óD  — |�;|                      d¦  «                             dd|j        d         ¦  «        }d|| <   t          | j        ||¬¦  «        }|                      |¦  «        }||                     |j        ¦  «        z   }|                      |¦  «        }|  	                    |¦  «        }t          ¦   «         pt          | ¦  «        }| j        D ]<}t          j        g ¦  «        }| j        o|| j        j        k     }	|	r|r ||fd|i|¤Ž}Œ=t#          |¬¦  «        S )Nr@   r   rO   r   )r9   Úinputs_embedsr•   r•   )Úlast_hidden_state)Ú	unsqueezeÚrepeatr·   r   r9   rç   ÚtoÚdevicer4   rŒ   r
   r   rj   rž   Úrandr~   Ú	layerdropr   )
r8   rC   r•   r—   Úexpand_attention_maskÚposition_embeddingsÚsynced_gpusrl   Údropout_probabilityÚskip_the_layers
             r<   rD   zData2VecAudioEncoder.forwardg  sK  € ð Ð%à$2×$<Ò$<¸RÑ$@Ô$@×$GÒ$GÈÈ1ÈmÔNaÐbcÔNdÑ$eÔ$eÐ!Ø45ˆMÐ0Ð0Ñ1å2Ø”;Ø'Ø)ð
ñ 
ô 
ˆð #×1Ò1°-Ñ@Ô@ÐØ%Ð(;×(>Ò(>¸}Ô?SÑ(TÔ(TÑTˆØŸš¨Ñ6Ô6ˆØŸš ]Ñ3Ô3ˆå0Ñ2Ô2ÐRÕ6LÈTÑ6RÔ6Rˆà”[ð 	^ð 	^ˆEå"'¤*¨R¡.¤.Ðà!œ]ÐZÐ/BÀTÄ[ÔEZÒ/ZˆNØ!ð ^ [ð ^à %  mÐ ]Ð ]ÀNÐ ]ÐV\Ð ]Ð ]�øå°Ð?Ñ?Ô?Ð?r=   rŽ   )rG   rH   rI   r*   rž   ÚtensorrÈ   r   r   rD   rJ   rK   s   @r<   rä   rä   ]  s�   ø€ € € € € ð,ð ,ð ,ð ,ð ,ð /3ð!@ð !@à”|ð!@ð œ tÑ+ð!@ð Ð+Ô,ð	!@ð !@ð !@ð !@ð !@ð !@ð !@ð !@r=   rä   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚData2VecAudioAdapterLayerc                 ó²   •— t          ¦   «                              ¦   «          t          j        |j        d|j        z  |j        |j        d¬¦  «        | _        d S )NrO   r   )r%   rW   )r)   r*   r   r.   Úoutput_hidden_sizeÚadapter_kernel_sizeÚadapter_strider2   r\   s     €r<   r*   z"Data2VecAudioAdapterLayer.__init__Œ  sU   ø€ Ý‰Œ×ÒÑÔÐÝ”IØÔ%Ø�Ô)Ñ)ØÔ&ØÔ(Øð
ñ 
ô 
ˆŒ	ˆ	ˆ	r=   c                 ór   — |                       |¦  «        }t          j                             |d¬¦  «        }|S )Nr   rš   )r2   r   r    ÚglurB   s     r<   rD   z!Data2VecAudioAdapterLayer.forward–  s3   € ØŸ	š	 -Ñ0Ô0ˆÝœ×)Ò)¨-¸QÐ)Ñ?Ô?ˆàÐr=   rF   rK   s   @r<   rù   rù   ‹  sG   ø€ € € € € ð
ð 
ð 
ð 
ð 
ðð ð ð ð ð ð r=   rù   c                   ó$   ‡ — e Zd Zˆ fd„Zd„ Zˆ xZS )ÚData2VecAudioAdapterc                 ó’  •‡— t          ¦   «                              ¦   «          ‰j        ‰j        k    rCt	          j        ‰j        ‰j        ¦  «        | _        t	          j        ‰j        ¦  «        | _        nd x| _        | _        t	          j	        ˆfd„t          ‰j        ¦  «        D ¦   «         ¦  «        | _        ‰j        | _        d S )Nc              3   ó6   •K  — | ]}t          ‰¦  «        V — Œd S rŽ   )rù   rd   s     €r<   ú	<genexpr>z0Data2VecAudioAdapter.__init__.<locals>.<genexpr>¨  s,   øè è € Ð#pÐ#pÈ!Õ$=¸fÑ$EÔ$EÐ#pÐ#pÐ#pÐ#pÐ#pÐ#pr=   )r)   r*   rû   rY   r   rˆ   Úprojr3   Úproj_layer_normrh   ri   Únum_adapter_layersrj   rñ   r\   s    `€r<   r*   zData2VecAudioAdapter.__init__ž  s­   øø€ Ý‰Œ×ÒÑÔÐð Ô$¨Ô(:Ò:Ð:Ýœ	 &Ô"4°fÔ6OÑPÔPˆDŒIÝ#%¤<°Ô0IÑ#JÔ#JˆDÔ Ð à/3Ð3ˆDŒI˜Ô,å”mÐ#pÐ#pÐ#pÐ#pÍuÐU[ÔUnÑOoÔOoÐ#pÑ#pÔ#pÑpÔpˆŒØÔ)ˆŒˆˆr=   c                 óX  — | j         �1| j        �*|                       |¦  «        }|                      |¦  «        }|                     dd¦  «        }| j        D ]=}t          j                             ¦   «         }| j        r|| j        k    r ||¦  «        }Œ>|                     dd¦  «        }|S r^   )r  r  rA   rj   ÚnpÚrandomr~   rñ   )r8   rC   rl   Úlayerdrop_probs       r<   rD   zData2VecAudioAdapter.forward«  s°   € àŒ9Ð  TÔ%9Ð%EØ ŸIšI mÑ4Ô4ˆMØ ×0Ò0°Ñ?Ô?ˆMà%×/Ò/°°1Ñ5Ô5ˆà”[ð 	5ð 	5ˆEÝœY×-Ò-Ñ/Ô/ˆNØ”=ð 5 ^°d´nÒ%DÐ%DØ %  mÑ 4Ô 4�øà%×/Ò/°°1Ñ5Ô5ˆØÐr=   rF   rK   s   @r<   r  r  �  sG   ø€ € € € € ð*ð *ð *ð *ð *ðð ð ð ð ð ð r=   r  c                   óØ   ‡ — 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        ¦   «         ˆ fd
„¦   «         Zddej        ez  dedz  fd„Z	 ddedej        fd„Zˆ xZS )ÚData2VecAudioPreTrainedModelr9   Údata2vec_audior   ÚaudioTr   Úencoder)ÚindexÚ
layer_name)rC   Ú
attentionsc                 óÂ  •— t          ¦   «                              |¦  «         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_weightsrÑ   rƒ   ÚmathÚsqrtr‰   Úin_featuresÚinitÚuniform_Úweightr&   rU   Ú	constant_r2   r   r.   Úkaiming_normal_rX   Úin_channelsr$   )r8   r‘   Úkr;   s      €r<   r  z*Data2VecAudioPreTrainedModel._init_weightsË  sG  ø€ õ 	‰Œ×Ò˜fÑ%Ô%Ð%Ý�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&r=   NÚinput_lengthsÚadd_adapterc                 ó  — |€| j         j        n|}d„ }t          | j         j        | j         j        ¦  «        D ]\  }} ||||¦  «        }Œ|r3t          | j         j        ¦  «        D ]} ||d| j         j        ¦  «        }Œ|S )zH
        Computes the output length of the convolutional layers
        Nc                 ó<   — t          j        | |z
  |d¬¦  «        dz   S )NÚfloor)Úrounding_moder   )rž   Údiv©Úinput_lengthr$   r%   s      r<   Ú_conv_out_lengthzWData2VecAudioPreTrainedModel._get_feat_extract_output_lengths.<locals>._conv_out_lengthã  s&   € õ ”9˜\¨KÑ7¸ÈwÐWÑWÔWÐZ[Ñ[Ð[r=   r   )r9   r#  Úzipr/   r0   ri   r  rý   )r8   r"  r#  r+  r$   r%   rf   s          r<   Ú _get_feat_extract_output_lengthsz=Data2VecAudioPreTrainedModel._get_feat_extract_output_lengthsÜ  s´   € ð
 2=Ð1D�d”kÔ-Ð-È+ˆð	\ð 	\ð 	\õ
 $' t¤{Ô'>ÀÄÔ@WÑ#XÔ#Xð 	Qð 	QÑˆK˜Ø,Ð,¨]¸KÈÑPÔPˆMˆMàð 	_Ý˜4œ;Ô9Ñ:Ô:ð _ð _�Ø 0Ð 0°ÀÀ4Ä;ÔC]Ñ ^Ô ^��àÐr=   Úfeature_vector_lengthr•   c                 ó  — |                      d¬¦  «        d d …df         }|                      ||¬¦  «        }|                     t          j        ¦  «        }|j        d         }t          j        ||f|j        |j        ¬¦  «        }d|t          j	        |j        d         |j        ¬¦  «        |dz
  f<   | 
                    dg¦  «                              d¦  «         
                    dg¦  «                             ¦   «         }|S )Nr@   rš   ©r#  r   )Údtyperï   r   )rï   )Úcumsumr-  rî   rž   Úlongr·   Úzerosr1  rï   ÚarangeÚfliprÇ   )r8   r.  r•   r#  Únon_padded_lengthsÚoutput_lengthsÚ
batch_sizes          r<   Ú"_get_feature_vector_attention_maskz?Data2VecAudioPreTrainedModel._get_feature_vector_attention_maskñ  s  € ð
 ,×2Ò2°rÐ2Ñ:Ô:¸1¸1¸1¸b¸5ÔAÐà×>Ò>Ð?QÐ_jÐ>ÑkÔkˆØ'×*Ò*­5¬:Ñ6Ô6ˆà#Ô)¨!Ô,ˆ
åœØÐ.Ð/°~Ô7KÐTbÔTið
ñ 
ô 
ˆð uvˆ�œ ^Ô%9¸!Ô%<À^ÔEZÐ[Ñ[Ô[Ð]kÐnoÑ]oÐpÑqØ'×,Ò,¨b¨TÑ2Ô2×9Ò9¸"Ñ=Ô=×BÒBÀBÀ4ÑHÔH×MÒMÑOÔOˆØÐr=   rŽ   )rG   rH   rI   r    Ú__annotations__Úbase_model_prefixÚmain_input_nameÚinput_modalitiesÚsupports_gradient_checkpointingÚ_supports_flash_attnÚ_supports_sdpaÚ_supports_flex_attnrÚ   r   r§   Ú_can_record_outputsrž   Úno_gradr  Ú
LongTensorrÅ   rÇ   r-  r:  rJ   rK   s   @r<   r  r  ¼  s  ø€ € € € € € àÐÐÑØ(ÐØ$€OØÐØ&*Ð#ØÐØ€NØÐà2Ø$�nÐ%;À1ÐQZÐ[Ñ[Ô[ðð Ðð
 €U„]�_„_ð6ð 6ð 6ð 6ñ „_ð6ð ð ¸eÔ>NÐQTÑ>Tð ÐcgÐjnÑcnð ð ð ð ð, Y]ðð Ø%(ðØ:?Ô:Jðð ð ð ð ð ð ð r=   r  r·   Ú	mask_probÚmask_lengthÚ	min_masksrµ   c                 ó@  ‡‡‡‡‡— | \  }Š‰dk     rt          d¦  «        ‚‰‰k    rt          d‰› d‰› d�¦  «        ‚t          j                             d¦  «                             ¦   «         Šˆˆˆˆˆfd„}|�9|                     ¦   «                              d¦  «                             ¦   «         nˆfd	„t          |¦  «        D ¦   «         }t          j	        |‰ft          ¬
¦  «        }g }	 |‰¦  «        }
|
dk    r|S |D ]·} ||¦  «        }t          j                             t          j        |‰dz
  z
  ¦  «        |d¬¦  «        }t          |¦  «        dk    r‰dz
  }n|d         }t          j        |t          j        |
|z
  t          j        ¬
¦  «        |z  g¦  «        }|	                     |¦  «         Œ¸t          j        |	¦  «        }	t          j        |	dd…dd…df         ||
‰f¦  «        }	|	                     ||
‰z  ¦  «        }	t          j        ‰¦  «        dddd…f         }t          j        |||
‰f¦  «                             ||
‰z  ¦  «        }|	|z   }	|	                     ¦   «         ‰dz
  k    r‰dz
  |	|	‰dz
  k    <   t          j        ||	dd¦  «         |S )an  
    Computes random mask spans for a given shape. Used to implement [SpecAugment: A Simple Data Augmentation Method for
    ASR](https://huggingface.co/papers/1904.08779). Note that this method is not optimized to run on TPU and should be run on
    CPU as part of the preprocessing during training.

    Args:
        shape: The shape for which to compute masks. This should be of a tuple of size 2 where
               the first element is the batch size and the second element is the length of the axis to span.
        mask_prob:  The percentage of the whole axis (between 0 and 1) which will be masked. The number of
                    independently generated mask spans of length `mask_length` is computed by
                    `mask_prob*shape[1]/mask_length`. Note that due to overlaps, `mask_prob` is an upper bound and the
                    actual percentage will be smaller.
        mask_length: size of the mask
        min_masks: minimum number of masked spans
        attention_mask: A (right-padded) attention mask which independently shortens the feature axis of
                        each batch dimension.
    r   z&`mask_length` has to be bigger than 0.zO`mask_length` has to be smaller than `sequence_length`, but got `mask_length`: z and `sequence_length`: ú`c                 ó¸   •— t          ‰| z  ‰z  ‰z   ¦  «        }t          |‰¦  «        }|‰z  ‰k    r‰‰z  }| ‰dz
  z
  |k     rt          | ‰dz
  z
  d¦  «        }|S )z;Given input length, compute how many spans should be maskedr   r   )rÅ   Úmax)r*  Únum_masked_spanÚepsilonrG  rF  rH  Úsequence_lengths     €€€€€r<   Úcompute_num_masked_spanz6_compute_mask_indices.<locals>.compute_num_masked_span,  s~   ø€ å˜i¨,Ñ6¸ÑDÀwÑNÑOÔOˆÝ˜o¨yÑ9Ô9ˆð ˜[Ñ(¨?Ò:Ð:Ø-°Ñ<ˆOð ˜;¨™?Ñ+¨oÒ=Ð=Ý! ,°+À±/Ñ"BÀAÑFÔFˆOàÐr=   Nr@   c                 ó   •— g | ]}‰‘ŒS rc   rc   )re   rf   rO  s     €r<   rg   z)_compute_mask_indices.<locals>.<listcomp>?  s   ø€ Ð9Ð9Ð9 !ˆoÐ9Ð9Ð9r=   ©r1  r   F)Úreplace)r®   r	  r
  rð   ÚitemÚdetachÚsumÚtolistri   r4  rÇ   Úchoicer5  ÚlenÚconcatenateÚonesÚint32ÚappendÚarrayÚbroadcast_tor»   rL  Úput_along_axis)r·   rF  rG  r•   rH  r9  rP  r"  Úspec_aug_maskÚspec_aug_mask_idxsÚmax_num_masked_spanr*  rM  Úspec_aug_mask_idxÚdummy_mask_idxÚoffsetsrN  rO  s    `` `           @@r<   Ú_compute_mask_indicesrg    sP  øøøøø€ ð0 #(Ñ€J�à�Q‚€ÝÐAÑBÔBÐBà�_Ò$Ð$Ýð:Ð^ið :ð :Ø'6ð:ð :ð :ñ
ô 
ð 	
õ Œi�nŠn˜QÑÔ×$Ò$Ñ&Ô&€Gðð ð ð ð ð ð ð ð ð$ Ð%ð 	×ÒÑÔ×#Ò# BÑ'Ô'×.Ò.Ñ0Ô0Ð0à9Ð9Ð9Ð9¥u¨ZÑ'8Ô'8Ð9Ñ9Ô9ð õ ”H˜j¨/Ð:Å$ÐGÑGÔG€MØÐà1Ð1°/ÑBÔBÐà˜aÒÐØÐà%ð 5ð 5ˆà1Ð1°,Ñ?Ô?ˆõ œI×,Ò,ÝŒI�l k°A¡oÑ6Ñ7Ô7¸ÐRWð -ñ 
ô 
Ðõ Ð Ñ!Ô! QÒ&Ð&ð -¨qÑ0ˆNˆNà.¨qÔ1ˆNåœNØ¥¤Ð(;¸oÑ(MÕUWÔU]Ð ^Ñ ^Ô ^ÐaoÑ oÐpñ
ô 
Ðð 	×!Ò!Ð"3Ñ4Ô4Ð4Ð4åœÐ"4Ñ5Ô5Ðõ œØ˜1˜1˜1˜a˜a˜a ˜:Ô&¨Ð5HÈ+Ð(Vñô Ðð ,×3Ò3°JÐ@SÐVaÑ@aÑbÔbÐõ Œi˜Ñ$Ô$ T¨4°°° ]Ô3€GÝŒo˜g¨
Ð4GÈÐ'UÑVÔV×^Ò^ØÐ'¨+Ñ5ñô €Gð ,¨gÑ5Ðð ×ÒÑÔ /°AÑ"5Ò5Ð5ØGVÐYZÑGZÐÐ-°À!Ñ0CÒCÑDõ Ô�mÐ%7¸¸BÑ?Ô?Ð?àÐr=   c                   ó  ‡ — e Zd Zdefˆ fd„Zd„ Z	 	 ddej        dej        dz  dej        dz  fd„Z	e
 ed	¬
¦  «        e	 	 ddej        dz  dej        dz  dej        dz  dee         deez  f
d„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚData2VecAudioModelr9   c                 óâ  •— t          ¦   «                              |¦  «         || _        t          |¦  «        | _        t          |¦  «        | _        |j        dk    s|j        dk    rBt          j
        t          j        |j        ¦  «                             ¦   «         ¦  «        | _        t!          |¦  «        | _        |j        rt'          |¦  «        nd | _        |                      ¦   «          d S ©Nr�   )r)   r*   r9   rn   Úfeature_extractorrƒ   Úfeature_projectionÚmask_time_probÚmask_feature_probr   Ú	Parameterrž   rÈ   rY   r  Úmasked_spec_embedrä   r  r#  r  ÚadapterÚ	post_initr\   s     €r<   r*   zData2VecAudioModel.__init__‚  sÎ   ø€ Ý‰Œ×Ò˜Ñ 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r=   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)rl  r|   ©r8   s    r<   Úfreeze_feature_encoderz)Data2VecAudioModel.freeze_feature_encoder“  s   € ð
 	Ô×1Ò1Ñ3Ô3Ð3Ð3Ð3r=   NrC   Úmask_time_indicesr•   c                 ó  — t          | j        dd¦  «        s|S |                     ¦   «         \  }}}|�#| j                             |j        ¦  «        ||<   n“| j        j        dk    rƒ| j        r|t          ||f| j        j        | j        j	        || j        j
        ¬¦  «        }t          j        ||j        t          j        ¬¦  «        }| j                             |j        ¦  «        ||<   | j        j        dk    r†| j        rt          ||f| j        j        | j        j        | j        j        ¬¦  «        }t          j        ||j        t          j        ¬¦  «        }|dd…df                              d|d¦  «        }d||<   |S )	z¢
        Masks extracted features along time axis and/or along feature axis according to
        [SpecAugment](https://huggingface.co/papers/1904.08779).
        Úapply_spec_augmentTNr   )rF  rG  r•   rH  )rï   r1  )rF  rG  rH  r@   )Úgetattrr9   r�   rq  rî   r1  rn  r~   rg  Úmask_time_lengthÚmask_time_min_masksrž   r÷   rï   rÇ   ro  Úmask_feature_lengthÚmask_feature_min_masksÚexpand)r8   rC   rx  r•   r9  rO  rY   Úmask_feature_indicess           r<   Ú_mask_hidden_statesz&Data2VecAudioModel._mask_hidden_statesš  s—  € õ �t”{Ð$8¸$Ñ?Ô?ð 	!Ø Ð ð 4A×3EÒ3EÑ3GÔ3GÑ0ˆ
�O [àÐ(à/3Ô/E×/HÒ/HÈÔI\Ñ/]Ô/]ˆMÐ+Ñ,Ð,ØŒ[Ô'¨!Ò+Ð+°´Ð+Ý 5Ø˜_Ð-Øœ+Ô4Ø œKÔ8Ø-Øœ+Ô9ð!ñ !ô !Ðõ !&¤Ð->À}ÔG[ÕchÔcmÐ nÑ nÔ nÐØ/3Ô/E×/HÒ/HÈÔI\Ñ/]Ô/]ˆMÐ+Ñ,àŒ;Ô(¨1Ò,Ð,°´Ð,å#8Ø˜[Ð)Øœ+Ô7Ø œKÔ;Øœ+Ô<ð	$ñ $ô $Ð õ $)¤<Ð0DÈ]ÔMaÕinÔisÐ#tÑ#tÔ#tÐ Ø#7¸¸¸¸4¸Ô#@×#GÒ#GÈÈOÐ]_Ñ#`Ô#`Ð Ø23ˆMÐ.Ñ/àÐr=   F)Útie_last_hidden_statesr   r—   rµ   c                 óŠ  — |                       |¦  «        }|                     dd¦  «        }|�#|                      |j        d         |d¬¦  «        }|                      |¦  «        \  }}|                      |||¬¦  «        } | j        |fd|i|¤Ž}|j        }| j        �|                      |¦  «        }t          ||¬¦  «        S )	a/  
        mask_time_indices (`torch.BoolTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Indices to mask extracted features for contrastive loss. When in training mode, model learns to predict
            masked extracted features in *config.proj_codevector_dim* space.
        r   rO   NFr0  )rx  r•   r•   )rë   Úextract_features)
rl  rA   r:  r·   rm  r‚  r  rë   rr  ÚData2VecAudioBaseModelOutput)r8   r   r•   rx  r—   r…  rC   Úencoder_outputss           r<   rD   zData2VecAudioModel.forwardÈ  s  € ð  ×1Ò1°,Ñ?Ô?ÐØ+×5Ò5°a¸Ñ;Ô;ÐàÐ%à!×DÒDØ Ô& qÔ)¨>Àuð Eñ ô ˆNð +/×*AÒ*AÐBRÑ*SÔ*SÑ'ˆÐ'Ø×0Ò0ØÐ->È~ð 1ñ 
ô 
ˆð '˜$œ,Øð
ð 
à)ð
ð ð
ð 
ˆð (Ô9ˆàŒ<Ð#Ø ŸLšL¨Ñ7Ô7ˆMå+Ø+Ø-ð
ñ 
ô 
ð 	
r=   ©NN)rG   rH   rI   r    r*   rw  rž   ÚFloatTensorrE  r‚  r   r   r   rÈ   r   r   rÉ   r†  rD   rJ   rK   s   @r<   ri  ri  €  sG  ø€ € € € € ðÐ2ð ð ð ð ð ð ð"4ð 4ð 4ð 7;Ø26ð	,ð ,àÔ(ð,ð !Ô,¨tÑ3ð,ð Ô(¨4Ñ/ð	,ð ,ð ,ð ,ð\  Ø€_¨EÐ2Ñ2Ô2Øð /3Ø6:ð	(
ð (
à”l TÑ)ð(
ð œ tÑ+ð(
ð !Ô,¨tÑ3ð	(
ð
 Ð+Ô,ð(
ð 
Ð-Ñ	-ð(
ð (
ð (
ñ „^ñ 3Ô2ñ  Ôð(
ð (
ð (
ð (
ð (
r=   ri  zu
    Data2VecAudio Model with a `language modeling` head on top for Connectionist Temporal Classification (CTC).
    )Úcustom_introc                   ó¨   ‡ — e Zd Zˆ fd„Zd„ Zee	 	 d
dej        dz  dej        dz  dej        dz  de	e
         deez  f
d	„¦   «         ¦   «         Zˆ xZS )ÚData2VecAudioForCTCc                 óœ  •— 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#  )r)   r*   ri  r  r   rŠ   Úfinal_dropoutrŒ   Ú
vocab_sizer®   r;   Úhasattrr#  rû   rY   rˆ   Úlm_headrs  )r8   r9   rû   r;   s      €r<   r*   zData2VecAudioForCTC.__init__ü  sÖ   ø€ õ 	‰Œ×Ò˜Ñ Ô Ð å0°Ñ8Ô8ˆÔÝ”z &Ô"6Ñ7Ô7ˆŒàÔÐ$ÝðH°´ð Hð Hð Hñô ð õ *1°¸Ñ)GÔ)GÐvÈFÔL^ÐvˆFÔ%Ð%ÐdjÔdvð 	õ ”yÐ!3°VÔ5FÑGÔGˆŒð 	�ŠÑÔÐÐÐr=   c                 óB   — | j         j                             ¦   «          dS ru  ©r  rl  r|   rv  s    r<   rw  z*Data2VecAudioForCTC.freeze_feature_encoder  ó"   € ð
 	ÔÔ-×@Ò@ÑBÔBÐBÐBÐBr=   Nr   r•   Úlabelsr—   rµ   c           
      óü  — |�>|                      ¦   «         | j        j        k    rt          d| j        j        › �¦  «        ‚ | j        |fd|i|¤Ž}|j        }|                      |¦  «        }|                      |¦  «        }d}|��Z|�|nt          j	        |t          j
        ¬¦  «        }|                      |                     d¦  «        ¦  «                             t          j
        ¦  «        }	|dk    }
|
                     d¦  «        }|                     |
¦  «        }t          j                             |dt          j        ¬¦  «                             dd¦  «        }t          j        j                             d	¬
¦  «        5  t          j                             |||	|| j        j        | j        j        | j        j        ¬¦  «        }ddd¦  «         n# 1 swxY w Y   t7          |||j        |j        ¬¦  «        S )aà  
        labels (`torch.LongTensor` of shape `(batch_size, target_length)`, *optional*):
            Labels for connectionist temporal classification. Note that `target_length` has to be smaller or equal to
            the sequence length of the output logits. Indices are selected in `[-100, 0, ..., config.vocab_size - 1]`.
            All labels set to `-100` are ignored (masked), the loss is only computed for labels in `[0, ...,
            config.vocab_size - 1]`.
        Nz$Label values must be <= vocab_size: r•   rR  r@   r   )r›   r1  r   F)Úenabled)ÚblankÚ	reductionÚzero_infinity©ÚlossÚlogitsrC   r  )rL  r9   r�  r®   r  rë   rŒ   r‘  rž   Ú	ones_liker3  r-  rV  rî   Úmasked_selectr   r    Úlog_softmaxÚfloat32rA   ÚbackendsÚcudnnÚflagsÚctc_lossÚpad_token_idÚctc_loss_reductionÚctc_zero_infinityr   rC   r  )r8   r   r•   r•  r—   ÚoutputsrC   r�  rœ  r"  Úlabels_maskÚtarget_lengthsÚflattened_targetsÚ	log_probss                 r<   rD   zData2VecAudioForCTC.forward  s;  € ð  Ð &§*¢*¡,¤,°$´+Ô2HÒ"HÐ"HÝÐ\ÀDÄKÔDZÐ\Ð\Ñ]Ô]Ð]à%�$Ô%Øð
ð 
à)ð
ð ð
ð 
ˆð  Ô1ˆØŸš ]Ñ3Ô3ˆà—’˜mÑ,Ô,ˆàˆØÑð #1Ð"<��Å%Ä/ÐR^ÕfkÔfpÐBqÑBqÔBqð ð !×AÒAÀ.×BTÒBTÐUWÑBXÔBXÑYÔY×\Ò\Õ]bÔ]gÑhÔhˆMð ! Aš+ˆKØ(Ÿ_š_¨RÑ0Ô0ˆNØ &× 4Ò 4°[Ñ AÔ AÐõ œ×1Ò1°&¸bÍÌÐ1ÑVÔV×`Ò`ÐabÐdeÑfÔfˆIå”Ô%×+Ò+°EÐ+Ñ:Ô:ð 	ð 	Ý”}×-Ò-ØØ%Ø!Ø"Øœ+Ô2Ø"œkÔ<Ø"&¤+Ô"?ð .ñ ô �ð	ð 	ð 	ñ 	ô 	ð 	ð 	ð 	ð 	ð 	ð 	øøøð 	ð 	ð 	ð 	õ Ø˜f°GÔ4IÐV]ÔVhð
ñ 
ô 
ð 	
s   ÆAGÇGÇGrˆ  )rG   rH   rI   r*   rw  r   r   rž   rÈ   r   r   rÉ   r   rD   rJ   rK   s   @r<   rŒ  rŒ  ö  sÒ   ø€ € € € € ðð ð ð ð ð6Cð Cð Cð Øð /3Ø&*ð	:
ð :
à”l TÑ)ð:
ð œ tÑ+ð:
ð ”˜tÑ#ð	:
ð
 Ð+Ô,ð:
ð 
�Ñ	ð:
ð :
ð :
ñ „^ñ Ôð:
ð :
ð :
ð :
ð :
r=   rŒ  zœ
    Data2VecAudio Model with a sequence classification head on top (a linear layer over the pooled output) for tasks like
    SUPERB Keyword Spotting.
    c                   ó¾   ‡ — e Zd Zˆ fd„Zd„ Zd„ Zeee	 	 dde	j
        dz  de	j
        dz  de	j
        dz  dee         d	eez  f
d
„¦   «         ¦   «         ¦   «         Zˆ xZS )Ú&Data2VecAudioForSequenceClassificationc                 óô  •— t          ¦   «                              |¦  «         t          |d¦  «        r|j        rt	          d¦  «        ‚t          |¦  «        | _        |j        dz   }|j        r.t          j
        t          j        |¦  «        |z  ¦  «        | _        t          j        |j        |j        ¦  «        | _        t          j        |j        |j        ¦  «        | _        |                      ¦   «          d S )Nr#  zdSequence classification does not support the use of Data2VecAudio adapters (config.add_adapter=True)r   )r)   r*   r�  r#  r®   ri  r  rè   Úuse_weighted_layer_sumr   rp  rž   r[  Úlayer_weightsrˆ   rY   Úclassifier_proj_sizeÚ	projectorÚ
num_labelsÚ
classifierrs  ©r8   r9   Ú
num_layersr;   s      €r<   r*   z/Data2VecAudioForSequenceClassification.__init__d  sâ   ø€ Ý‰Œ×Ò˜Ñ Ô Ð å�6˜=Ñ)Ô)ð 	¨fÔ.@ð 	ÝØvñô ð õ 1°Ñ8Ô8ˆÔØÔ-°Ñ1ˆ
ØÔ(ð 	SÝ!#¤­e¬j¸Ñ.DÔ.DÀzÑ.QÑ!RÔ!RˆDÔÝœ 6Ô#5°vÔ7RÑSÔSˆŒÝœ) FÔ$?ÀÔARÑSÔSˆŒð 	�ŠÑÔÐÐÐr=   c                 óB   — | j         j                             ¦   «          dS ru  r“  rv  s    r<   rw  z=Data2VecAudioForSequenceClassification.freeze_feature_encoderu  r”  r=   c                 óL   — | j                              ¦   «         D ]	}d|_        Œ
dS ©zÒ
        Calling this function will disable the gradient computation for the base model so that its parameters will not
        be updated during training. Only the classification head will be updated.
        FN©r  rx   ry   rz   s     r<   Úfreeze_base_modelz8Data2VecAudioForSequenceClassification.freeze_base_model|  ó7   € ð
 Ô(×3Ò3Ñ5Ô5ð 	(ð 	(ˆEØ"'ˆEÔÐð	(ð 	(r=   Nr   r•   r•  r—   rµ   c                 óæ  — | j         j        rd|d<    | j        |fd|i|¤Ž}| j         j        rr|j        }t	          j        |d¬¦  «        }t          j                             | j	        d¬¦  «        }|| 
                    ddd¦  «        z                       d¬¦  «        }n|j        }|                      |¦  «        }|€|                     d¬¦  «        }n�|                      |j        d         |¦  «        }	|	                     d¦  «                             dd|j        d         ¦  «        }
d	||
 <   |                     d¬¦  «        |	                     d¬¦  «         
                    dd¦  «        z  }|                      |¦  «        }d}|�Kt)          ¦   «         } || 
                    d| j         j        ¦  «        | 
                    d¦  «        ¦  «        }t-          |||j        |j        ¬
¦  «        S )á  
        input_values (`torch.FloatTensor` of shape `(batch_size, sequence_length)`):
            Float values of input raw speech waveform. Values can be obtained by loading a `.flac` or `.wav` audio file
            into an array of type `list[float]`, a `numpy.ndarray` or a `torch.Tensor`, *e.g.* via the torchcodec library
            (`pip install torchcodec`) or the soundfile library (`pip install soundfile`).
            To prepare the array into `input_values`, the [`AutoProcessor`] should be used for padding and conversion
            into a tensor of type `torch.FloatTensor`. See [`Data2VecAudioProcessor.__call__`] for details.
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        TÚoutput_hidden_statesr•   r   rš   r@   NrO   r�   r›  )r9   r±  r  rC   rž   Ústackr   r    r¡   r²  r¸   rV  rë   r´  Úmeanr:  r·   rì   rí   r¶  r   rµ  r   r  )r8   r   r•   r•  r—   r©  rC   Únorm_weightsÚpooled_outputÚpadding_maskÚexpand_padding_maskr�  rœ  Úloss_fcts                 r<   rD   z.Data2VecAudioForSequenceClassification.forward„  s  € ð, Œ;Ô-ð 	2Ø-1ˆFÐ)Ñ*à%�$Ô%Øð
ð 
à)ð
ð ð
ð 
ˆð Œ;Ô-ð 	6Ø#Ô1ˆMÝ!œK¨¸1Ð=Ñ=Ô=ˆMÝœ=×0Ò0°Ô1CÈÐ0ÑLÔLˆLØ*¨\×->Ò->¸rÀ1ÀaÑ-HÔ-HÑH×MÒMÐRSÐMÑTÔTˆMˆMà#Ô5ˆMàŸš }Ñ5Ô5ˆØÐ!Ø)×.Ò.°1Ð.Ñ5Ô5ˆMˆMà×BÒBÀ=ÔCVÐWXÔCYÐ[iÑjÔjˆLØ".×"8Ò"8¸Ñ"<Ô"<×"CÒ"CÀAÀqÈ-ÔJ]Ð^_ÔJ`Ñ"aÔ"aÐØ25ˆMÐ.Ð.Ñ/Ø)×-Ò-°!Ð-Ñ4Ô4°|×7GÒ7GÈAÐ7GÑ7NÔ7N×7SÒ7SÐTVÐXYÑ7ZÔ7ZÑZˆMà—’ Ñ/Ô/ˆàˆØÐÝ'Ñ)Ô)ˆHØ�8˜FŸKšK¨¨D¬KÔ,BÑCÔCÀVÇ[Â[ÐQSÁ_Ä_ÑUÔUˆDå'ØØØ!Ô/ØÔ)ð	
ñ 
ô 
ð 	
r=   rˆ  )rG   rH   rI   r*   rw  r½  r   r	   r   rž   rÈ   r   r   rÉ   r   rD   rJ   rK   s   @r<   r¯  r¯  ]  sí   ø€ € € € € ðð ð ð ð ð"Cð Cð Cð(ð (ð (ð Ø Øð /3Ø&*ð	9
ð 9
à”l TÑ)ð9
ð œ tÑ+ð9
ð ”˜tÑ#ð	9
ð
 Ð+Ô,ð9
ð 
Ð)Ñ	)ð9
ð 9
ð 9
ñ „^ñ !Ô ñ Ôð9
ð 9
ð 9
ð 9
ð 9
r=   r¯  c                   ó¾   ‡ — e Zd Zˆ fd„Zd„ Zd„ Zeee	 	 dde	j
        dz  de	j
        dz  de	j
        dz  dee         d	eez  f
d
„¦   «         ¦   «         ¦   «         Zˆ xZS )Ú(Data2VecAudioForAudioFrameClassificationc                 óÄ  •— t          ¦   «                              |¦  «         t          |d¦  «        r|j        rt	          d¦  «        ‚t          |¦  «        | _        |j        dz   }|j        r.t          j
        t          j        |¦  «        |z  ¦  «        | _        t          j        |j        |j        ¦  «        | _        |j        | _        |                      ¦   «          d S )Nr#  zgAudio frame classification does not support the use of Data2VecAudio adapters (config.add_adapter=True)r   )r)   r*   r�  r#  r®   ri  r  rè   r±  r   rp  rž   r[  r²  rˆ   rY   rµ  r¶  rs  r·  s      €r<   r*   z1Data2VecAudioForAudioFrameClassification.__init__Å  sÑ   ø€ Ý‰Œ×Ò˜Ñ Ô Ð å�6˜=Ñ)Ô)ð 	¨fÔ.@ð 	ÝØyñô ð õ 1°Ñ8Ô8ˆÔØÔ-°Ñ1ˆ
ØÔ(ð 	SÝ!#¤­e¬j¸Ñ.DÔ.DÀzÑ.QÑ!RÔ!RˆDÔÝœ) FÔ$6¸Ô8IÑJÔJˆŒØ Ô+ˆŒà�ŠÑÔÐÐÐr=   c                 óB   — | j         j                             ¦   «          dS ru  r“  rv  s    r<   rw  z?Data2VecAudioForAudioFrameClassification.freeze_feature_encoderÕ  r”  r=   c                 óL   — | j                              ¦   «         D ]	}d|_        Œ
dS r»  r¼  rz   s     r<   r½  z:Data2VecAudioForAudioFrameClassification.freeze_base_modelÜ  r¾  r=   Nr   r•   r•  r—   rµ   c           	      óz  — | j         j        rd|d<    | j        |fd|i|¤Ž}| j         j        rr|j        }t	          j        |d¬¦  «        }t          j                             | j	        d¬¦  «        }|| 
                    ddd¦  «        z                       d¬¦  «        }n|j        }|                      |¦  «        }d}	|�`t          ¦   «         }
 |
| 
                    d| j        ¦  «        t	          j        | 
                    d| j        ¦  «        d¬¦  «        ¦  «        }	t#          |	||j        |j        ¬	¦  «        S )
rÀ  TrÁ  r•   r   rš   r@   N)Úaxisr›  )r9   r±  r  rC   rž   rÂ  r   r    r¡   r²  r¸   rV  rë   r¶  r   rµ  Úargmaxr   r  )r8   r   r•   r•  r—   r©  rC   rÄ  r�  rœ  rÈ  s              r<   rD   z0Data2VecAudioForAudioFrameClassification.forwardä  s^  € ð, Œ;Ô-ð 	2Ø-1ˆFÐ)Ñ*à%�$Ô%Øð
ð 
à)ð
ð ð
ð 
ˆð Œ;Ô-ð 	6Ø#Ô1ˆMÝ!œK¨¸1Ð=Ñ=Ô=ˆMÝœ=×0Ò0°Ô1CÈÐ0ÑLÔLˆLØ*¨\×->Ò->¸rÀ1ÀaÑ-HÔ-HÑH×MÒMÐRSÐMÑTÔTˆMˆMà#Ô5ˆMà—’ Ñ/Ô/ˆàˆØÐÝ'Ñ)Ô)ˆHØ�8˜FŸKšK¨¨D¬OÑ<Ô<½e¼lÈ6Ï;Ê;ÐWYÐ[_Ô[jÑKkÔKkÐrsÐ>tÑ>tÔ>tÑuÔuˆDå$ØØØ!Ô/ØÔ)ð	
ñ 
ô 
ð 	
r=   rˆ  )rG   rH   rI   r*   rw  r½  r   r	   r   rž   rÈ   r   r   rÉ   r   rD   rJ   rK   s   @r<   rÊ  rÊ  Ã  sí   ø€ € € € € ðð ð ð ð ð Cð Cð Cð(ð (ð (ð Ø Øð /3Ø&*ð	0
ð 0
à”l TÑ)ð0
ð œ tÑ+ð0
ð ”˜tÑ#ð	0
ð
 Ð+Ô,ð0
ð 
Ð&Ñ	&ð0
ð 0
ð 0
ñ „^ñ !Ô ñ Ôð0
ð 0
ð 0
ð 0
ð 0
r=   rÊ  c                   ó&   ‡ — e Zd Zdˆ fd„	Zd„ Zˆ xZS )ÚAMSoftmaxLossç      >@çš™™™™™Ù?c                 óþ   •— t          ¦   «                              ¦   «          || _        || _        || _        t          j        t          j        ||¦  «        d¬¦  «        | _	        t          j
        ¦   «         | _        d S )NT)ry   )r)   r*   ÚscaleÚmarginrµ  r   rp  rž   Úrandnr  r   rœ  )r8   Ú	input_dimrµ  rÖ  r×  r;   s        €r<   r*   zAMSoftmaxLoss.__init__  se   ø€ Ý‰Œ×ÒÑÔÐØˆŒ
ØˆŒØ$ˆŒÝ”l¥5¤;¨y¸*Ñ#EÔ#EÐUYÐZÑZÔZˆŒÝÔ'Ñ)Ô)ˆŒ	ˆ	ˆ	r=   c                 óÐ  — |                      ¦   «         }t          j                             | j        d¬¦  «        }t          j                             |d¬¦  «        }t          j        ||¦  «        }|| j        z
  }t          j                             || j	        ¦  «        }| j
        t          j        |                     ¦   «         ||¦  «        z  }|                      ||¦  «        }|S )Nr   rš   r   )Úflattenr   r    Ú	normalizer  rž   Úmmr×  Úone_hotrµ  rÖ  ÚwhererÇ   rœ  )	r8   rC   r•  r  Ú	cos_thetaÚpsiÚonehotr�  rœ  s	            r<   rD   zAMSoftmaxLoss.forward#  s·   € Ø—’Ñ!Ô!ˆÝ”×(Ò(¨¬¸!Ð(Ñ<Ô<ˆÝœ×/Ò/°À1Ð/ÑEÔEˆÝ”H˜]¨FÑ3Ô3ˆ	Ø˜$œ+Ñ%ˆå”×&Ò& v¨t¬Ñ?Ô?ˆØ”�eœk¨&¯+ª+©-¬-¸¸iÑHÔHÑHˆØ�yŠy˜ Ñ(Ô(ˆàˆr=   )rÓ  rÔ  rF   rK   s   @r<   rÒ  rÒ    sL   ø€ € € € € ð*ð *ð *ð *ð *ð *ðð ð ð ð ð ð r=   rÒ  c                   óD   ‡ — e Zd Zdˆ fd„	Zdej        dej        fd„Zˆ xZS )Ú	TDNNLayerr   c                 óŒ  •— t          ¦   «                              ¦   «          |dk    r|j        |dz
           n|j        |         | _        |j        |         | _        |j        |         | _        |j        |         | _        t          j
        | j        | j        z  | j        ¦  «        | _        t          j        ¦   «         | _        d S )Nr   r   )r)   r*   Útdnn_dimr,   r-   Útdnn_kernelr$   Útdnn_dilationÚdilationr   rˆ   ÚkernelÚReLUr6   r7   s      €r<   r*   zTDNNLayer.__init__2  s¡   ø€ Ý‰Œ×ÒÑÔÐØ<DÀqºL¸L˜6œ?¨8°a©<Ô8Ð8ÈfÌoÐ^fÔNgˆÔØ"œO¨HÔ5ˆÔØ!Ô-¨hÔ7ˆÔØÔ,¨XÔ6ˆŒå”i Ô 0°4Ô3CÑ CÀTÔEVÑWÔWˆŒÝœ'™)œ)ˆŒˆˆr=   rC   rµ   c                 ó
  — t          ¦   «         rddlm} t          ¦   «         r)t          | j        |¦  «        rt          j        d¦  «         |                     dd¦  «        }| j        j         	                    | j
        | j        | j        ¦  «                             dd¦  «        }t          j                             ||| j        j        | j        ¬¦  «        }|                     dd¦  «        }|                      |¦  «        }|S )Nr   )Ú	LoraLayerz‡Detected LoRA on TDNNLayer. LoRA weights won't be applied due to optimization. You should exclude TDNNLayer from LoRA's target modules.r   rO   )ré  )r   Úpeft.tuners.lorarí  rÑ   rê  ÚwarningsÚwarnrA   r  r¸   r-   r$   r,   r   r    Úconv1dr&   ré  r6   )r8   rC   rí  r  s       r<   rD   zTDNNLayer.forward<  sÿ   € ÝÑÔð 	3Ø2Ð2Ð2Ð2Ð2Ð2åÑÔð 	Ý˜$œ+ yÑ1Ô1ð Ý”ðOñô ð ð &×/Ò/°°1Ñ5Ô5ˆØ”Ô#×(Ò(¨Ô):¸DÔ<LÈdÔN^Ñ_Ô_×iÒiÐjkÐmnÑoÔoˆÝœ×,Ò,¨]¸FÀDÄKÔDTÐ_cÔ_lÐ,ÑmÔmˆØ%×/Ò/°°1Ñ5Ô5ˆàŸš¨Ñ6Ô6ˆØÐr=   rE   )rG   rH   rI   r*   rž   rÈ   rD   rJ   rK   s   @r<   rä  rä  1  sc   ø€ € € € € ð$ð $ð $ð $ð $ð $ð U¤\ð °e´lð ð ð ð ð ð ð ð r=   rä  zq
    Data2VecAudio Model with an XVector feature extraction head on top for tasks like Speaker Verification.
    c                   óÚ   ‡ — e Zd Zˆ fd„Zd„ Zd„ Zdej        ez  fd„Z	e
ee	 	 ddej        dz  dej        dz  d	ej        dz  d
ee         deez  f
d„¦   «         ¦   «         ¦   «         Zˆ xZS )ÚData2VecAudioForXVectorc                 óÚ  •‡— t          ¦   «                              ‰¦  «         t          ‰¦  «        | _        ‰j        dz   }‰j        r.t          j        t          j	        |¦  «        |z  ¦  «        | _
        t          j        ‰j        ‰j        d         ¦  «        | _        ˆfd„t          t!          ‰j        ¦  «        ¦  «        D ¦   «         }t          j        |¦  «        | _        t          j        ‰j        d         dz  ‰j        ¦  «        | _        t          j        ‰j        ‰j        ¦  «        | _        t-          ‰j        ‰j        ¦  «        | _        |                      ¦   «          d S )Nr   r   c                 ó0   •— g | ]}t          ‰|¦  «        ‘ŒS rc   )rä  rq   s     €r<   rg   z4Data2VecAudioForXVector.__init__.<locals>.<listcomp>`  s#   ø€ ÐQÐQÐQ°•y ¨Ñ+Ô+ÐQÐQÐQr=   r@   rO   )r)   r*   ri  r  rè   r±  r   rp  rž   r[  r²  rˆ   rY   ræ  r´  ri   rY  rh   ÚtdnnÚxvector_output_dimrl  r¶  rÒ  rµ  Ú	objectivers  )r8   r9   r¸  Útdnn_layersr;   s    `  €r<   r*   z Data2VecAudioForXVector.__init__W  s(  øø€ Ý‰Œ×Ò˜Ñ Ô Ð å0°Ñ8Ô8ˆÔØÔ-°Ñ1ˆ
ØÔ(ð 	SÝ!#¤­e¬j¸Ñ.DÔ.DÀzÑ.QÑ!RÔ!RˆDÔÝœ 6Ô#5°v´ÀqÔ7IÑJÔJˆŒàQÐQÐQÐQµU½3¸v¼Ñ;OÔ;OÑ5PÔ5PÐQÑQÔQˆÝ”M +Ñ.Ô.ˆŒ	å!#¤¨6¬?¸2Ô+>ÀÑ+BÀFÔD]Ñ!^Ô!^ˆÔÝœ) FÔ$=¸vÔ?XÑYÔYˆŒå& vÔ'@À&ÔBSÑTÔTˆŒà�ŠÑÔÐÐÐr=   c                 óB   — | j         j                             ¦   «          dS ru  r“  rv  s    r<   rw  z.Data2VecAudioForXVector.freeze_feature_encoderj  r”  r=   c                 óL   — | j                              ¦   «         D ]	}d|_        Œ
dS r»  r¼  rz   s     r<   r½  z)Data2VecAudioForXVector.freeze_base_modelq  r¾  r=   r"  c                 óD   — d„ }| j         j        D ]} |||d¦  «        }Œ|S )z?
        Computes the output length of the TDNN layers
        c                 ó   — | |z
  |z  dz   S )Nr   rc   r)  s      r<   r+  zJData2VecAudioForXVector._get_tdnn_output_lengths.<locals>._conv_out_length~  s   € ð ! ;Ñ.°6Ñ9¸AÑ=Ð=r=   r   )r9   rç  )r8   r"  r+  r$   s       r<   Ú_get_tdnn_output_lengthsz0Data2VecAudioForXVector._get_tdnn_output_lengthsy  sE   € ð
	>ð 	>ð 	>ð
  œ;Ô2ð 	Lð 	LˆKØ,Ð,¨]¸KÈÑKÔKˆMˆMàÐr=   Nr   r•   r•  r—   rµ   c                 ó¾  — | j         j        rd|d<    | j        |fd|i|¤Ž}| j         j        rr|j        }t	          j        |d¬¦  «        }t          j                             | j	        d¬¦  «        }|| 
                    ddd¦  «        z                       d¬¦  «        }n|j        }|                      |¦  «        }| j        D ]} ||¦  «        }Œ|€-|                     d¬¦  «        }	|                     d¬¦  «        }
nå|                      |                     d¬¦  «        ¦  «        }|                      |¦  «        }g }	g }
t'          |¦  «        D ]k\  }}|	                     ||d|…f                              d¬¦  «        ¦  «         |
                     ||d|…f                              d¬¦  «        ¦  «         Œlt	          j        |	¦  «        }	t	          j        |
¦  «        }
t	          j        |	|
gd¬¦  «        }|                      |¦  «        }|                      |¦  «        }d}|�|                      ||¦  «        }t3          ||||j        |j        ¬	¦  «        S )
rÀ  TrÁ  r•   r   rš   r@   Nr   )rœ  r�  Ú
embeddingsrC   r  )r9   r±  r  rC   rž   rÂ  r   r    r¡   r²  r¸   rV  rë   r´  rö  rÃ  Ústdr-  rþ  Ú	enumerater]  Úcatrl  r¶  rø  r   r  )r8   r   r•   r•  r—   r©  rC   rÄ  Ú
tdnn_layerÚmean_featuresÚstd_featuresÚfeat_extract_output_lengthsÚtdnn_output_lengthsrr   ÚlengthÚstatistic_poolingÚoutput_embeddingsr�  rœ  s                      r<   rD   zData2VecAudioForXVector.forwardˆ  s§  € ð, Œ;Ô-ð 	2Ø-1ˆFÐ)Ñ*à%�$Ô%Øð
ð 
à)ð
ð ð
ð 
ˆð Œ;Ô-ð 	6Ø#Ô1ˆMÝ!œK¨¸1Ð=Ñ=Ô=ˆMÝœ=×0Ò0°Ô1CÈÐ0ÑLÔLˆLØ*¨\×->Ò->¸rÀ1ÀaÑ-HÔ-HÑH×MÒMÐRSÐMÑTÔTˆMˆMà#Ô5ˆMàŸš }Ñ5Ô5ˆàœ)ð 	6ð 	6ˆJØ&˜J }Ñ5Ô5ˆMˆMð Ð!Ø)×.Ò.°1Ð.Ñ5Ô5ˆMØ(×,Ò,°Ð,Ñ3Ô3ˆLˆLà*.×*OÒ*OÐP^×PbÒPbÐghÐPbÑPiÔPiÑ*jÔ*jÐ'Ø"&×"?Ò"?Ð@[Ñ"\Ô"\ÐØˆMØˆLÝ&Ð':Ñ;Ô;ð Jð J‘	��6Ø×$Ò$ ]°1°g°v°g°:Ô%>×%CÒ%CÈÐ%CÑ%JÔ%JÑKÔKÐKØ×#Ò# M°!°W°f°W°*Ô$=×$AÒ$AÀaÐ$AÑ$HÔ$HÑIÔIÐIÐIÝ!œK¨Ñ6Ô6ˆMÝ œ; |Ñ4Ô4ˆLÝ!œI }°lÐ&CÈÐLÑLÔLÐà ×2Ò2Ð3DÑEÔEÐØ—’Ð!2Ñ3Ô3ˆàˆØÐØ—>’> &¨&Ñ1Ô1ˆDåØØØ(Ø!Ô/ØÔ)ð
ñ 
ô 
ð 	
r=   rˆ  )rG   rH   rI   r*   rw  r½  rž   rE  rÅ   rþ  r   r	   r   rÈ   r   r   rÉ   r   rD   rJ   rK   s   @r<   ró  ró  Q  s  ø€ € € € € ðð ð ð ð ð&Cð Cð Cð(ð (ð (ð°eÔ6FÈÑ6Lð ð ð ð ð Ø Øð /3Ø&*ð	F
ð F
à”l TÑ)ðF
ð œ tÑ+ðF
ð ”˜tÑ#ð	F
ð
 Ð+Ô,ðF
ð 
�Ñ	ðF
ð F
ð F
ñ „^ñ !Ô ñ ÔðF
ð F
ð F
ð F
ð F
r=   ró  )rÊ  rŒ  r¯  ró  ri  r  rk  rS   )Rr  rï  Úcollections.abcr   Únumpyr	  rž   r   Útorch.nnr   Ú r   r  Úactivationsr   Úbackbone_utilsr	   Úintegrations.deepspeedr
   Úintegrations.fsdpr   Úmasking_utilsr   Úmodeling_flash_attention_utilsr   Úmodeling_layersr   Úmodeling_outputsr   r   r   r   r   r   Úmodeling_utilsr   r   Úprocessing_utilsr   Úutilsr   r   r   Úutils.genericr   r   Úutils.output_capturingr   r   Úconfiguration_data2vec_audior    r"   ÚModulerM   rU   r`   rn   rƒ   rÈ   rÆ   r¥   r§   rË   rÚ   rä   rù   r  r  rÉ   rÅ   rE  Úndarrayrg  r†  ri  rŒ  r¯  rÊ  rÒ  rä  ró  Ú__all__rc   r=   r<   ú<module>r!     s/  ðð* €€€Ø €€€Ø $Ð $Ð $Ð $Ð $Ð $à Ð Ð Ð Ø €€€Ø Ð Ð Ð Ð Ð 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 @Ð @Ð @Ð @Ð @Ð @Ø 7Ð 7Ð 7Ð 7Ð 7Ð 7Ø 6Ð 6Ð 6Ð 6Ð 6Ð 6Ø BÐ BÐ BÐ BÐ BÐ BØ 9Ð 9Ð 9Ð 9Ð 9Ð 9ðð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð GÐ FÐ FÐ FÐ FÐ FÐ FÐ FØ &Ð &Ð &Ð &Ð &Ð &Ø JÐ JÐ JÐ JÐ JÐ JÐ JÐ JÐ JÐ JØ IÐ IÐ IÐ IÐ IÐ IÐ IÐ IØ EÐ EÐ EÐ EÐ EÐ EÐ EÐ EØ =Ð =Ð =Ð =Ð =Ð =ðð ð ð ð Ð7ñ ô ð ð6ð ð ð ð ˜BœIñ 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  "¤)ñ ô ð ð:1ð 1ð 1ð 1ð 1 R¤Yñ 1ô 1ð 1ð* !Øð%ð %ØŒIð%àŒ<ð%ð 
Œð%ð Œ<ð	%ð
 ”L 4Ñ'ð%ð �T‰\ð%ð ð%ð Ð'Ô(ð%ð %ð %ð %ð8R)ð R)ð R)ð R)ð R)˜RœYñ R)ô R)ð R)ðjð ð ð ð ˜rœyñ ô ð ð0ð ð ð ð Ð :ñ ô ð ðD+@ð +@ð +@ð +@ð +@˜2œ9ñ +@ô +@ð +@ð\ð ð ð ð  ¤	ñ ô ð ð$ð ð ð ð ˜2œ9ñ ô ð ð> ðFð Fð Fð Fð F ?ñ Fô Fñ „ðFðZ /3Øðtð tØ��c�Œ?ðtàðtð ðtð Ô$ tÑ+ð	tð
 ðtð „Zðtð tð tð tðn  7Ð ð ðr
ð r
ð r
ð r
ð r
Ð5ñ r
ô r
ñ „ðr
ðj €ððñ ô ð
_
ð _
ð _
ð _
ð _
Ð6ñ _
ô _
ñô ð
_
ðD €ððñ ô ð]
ð ]
ð ]
ð ]
ð ]
Ð-Iñ ]
ô ]
ñô ð]
ð@ ðS
ð S
ð S
ð S
ð S
Ð/Kñ S
ô S
ñ „ðS
ðlð ð ð ð �B”Iñ ô ð ð.ð ð ð ð �”	ñ ô ð ð@ €ððñ ô ð
{
ð {
ð {
ð {
ð {
Ð:ñ {
ô {
ñô ð
{
ð|ð ð €€€r=   