
    i\k                     |   d Z ddlZddlmZ ddlm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mZ ddlmZmZ ddlmZ ddl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# ddl$m%Z%m&Z& e ed       G d de                    Z' G d dejP                        Z) G d dejP                        Z* G d de       Z+ G d de"      Z, G d  d!ejP                        Z- G d" d#e      Z.e G d$ d%e             Z/ ed&       G d' d(e/             Z0e G d) d*e             Z1 ed+       G d, d-e/             Z2g d.Z3y)/zPyTorch Parakeet model.    N)Callable)	dataclass)nn   )initialization)ACT2FN)GradientCheckpointingLayer)BaseModelOutputCausalLMOutput)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)ModelOutputTransformersKwargsauto_docstringcan_return_tuple)check_model_inputsmaybe_autocast   )%FastSpeech2ConformerConvolutionModule)LlamaAttentioneager_attention_forward   )ParakeetCTCConfigParakeetEncoderConfigz
    Extends [~modeling_outputs.BaseModelOutput] to include the output attention mask since sequence length is not preserved in the model's forward.
    )custom_introc                   6    e Zd ZU dZej
                  dz  ed<   y)ParakeetEncoderModelOutputNattention_mask)__name__
__module____qualname__r   torchTensor__annotations__     w/home/obispo/Crisostomo_bridge/mision_env/lib/python3.12/site-packages/transformers/models/parakeet/modular_parakeet.pyr   r   $   s     +/NELL4'.r'   r   c                        e Zd ZU dZej
                  ed<   ddef fdZ ej                         dej
                  fd       Z
 xZS )$ParakeetEncoderRelPositionalEncodingz*Relative positional encoding for Parakeet.inv_freqconfigc                 6   t         |           |j                  | _        d}d|t        j                  d|j
                  dt        j                        j                  |t        j                        |j
                  z  z  z  }| j                  d|d	       y )
N     @      ?r   r   dtype)devicer1   r+   F)
persistent)
super__init__max_position_embeddingsr#   arangehidden_sizeint64tofloatregister_buffer)selfr,   r2   baser+   	__class__s        r(   r5   z-ParakeetEncoderRelPositionalEncoding.__init__3   s    '-'E'E$Q 2 2AU[[ILLTZbgbmbmLn$$%
 	ZeDr'   hidden_statesc                    |j                   d   }|| j                  kD  rt        d| d| j                   d      t        j                  |dz
  | d|j
                        }| j                  d d d d f   j                         j                  |j                   d   dd      j                  |j
                        }|d d d d f   j                         }t        |j
                  j                  t              r/|j
                  j                  dk7  r|j
                  j                  nd	}t        |d
      5  |j                         |j                         z  j                  dd      }|j                         }|j!                         }	t        j"                  ||	gd      }
 |
j$                  g |
j                   d d d }
d d d        
j                  |j&                        S # 1 sw Y   %xY w)Nr   zSequence Length: z= has to be less or equal than config.max_position_embeddings .r2   r   mpscpuF)device_typeenabledr   dimr0   )shaper6   
ValueErrorr#   r7   r2   r+   r;   expandr:   
isinstancetypestrr   	transposesincosstackreshaper1   )r=   r@   
seq_lengthposition_idsinv_freq_expandedposition_ids_expandedrG   freqsrS   rT   	pos_embeds              r(   forwardz,ParakeetEncoderRelPositionalEncoding.forwardA   s   "((+
444#J< 02262N2N1OqR 
 ||JNZKML`L`aMM$4-(..0778K8KA8NPRTUVYYZgZnZno 	 !-T4] ; A A C -..33S9m>R>R>W>W[`>`   %% 	
 UC 	E&,,.1F1L1L1NNYYZ[]^_E))+C))+CS#JB7I)	))D9??3B+?DDI	E ||-"5"5|66	E 	Es   5BG%%G.N)r    r!   r"   __doc__r#   r$   r%   r   r5   no_gradr]   __classcell__r?   s   @r(   r*   r*   .   sF    4llE4 E U]]_7U\\ 7 7r'   r*   c                   *     e Zd Zdef fdZd Z xZS )ParakeetEncoderFeedForwardr,   c                 `   t         |           t        j                  |j                  |j
                  |j                        | _        t        |j                     | _
        t        j                  |j
                  |j                  |j                        | _        |j                  | _        y )Nbias)r4   r5   r   Linearr8   intermediate_sizeattention_biaslinear1r   
hidden_act
activationlinear2activation_dropoutr=   r,   r?   s     r(   r5   z#ParakeetEncoderFeedForward.__init__a   s|    yy!3!3V5M5MTZTiTij !2!23yy!9!96;M;MTZTiTij"(";";r'   c                     | j                  | j                  |            }t        j                  j	                  || j
                  | j                        }| j                  |      }|S )Nptraining)rm   rk   r   
functionaldropoutro   rt   rn   )r=   r@   s     r(   r]   z"ParakeetEncoderFeedForward.forwardh   sU    ](CD--mt?V?Vaeanan-o]3r'   )r    r!   r"   r   r5   r]   ra   rb   s   @r(   rd   rd   `   s    <4 <r'   rd   c                   &     e Zd Zddef fdZ xZS ) ParakeetEncoderConvolutionModuler,   c                 &    t         |   ||       y r^   )r4   r5   )r=   r,   module_configr?   s      r(   r5   z)ParakeetEncoderConvolutionModule.__init__p   s    /r'   r^   )r    r!   r"   r   r5   ra   rb   s   @r(   rx   rx   o   s    04 0 0r'   rx   c                        e Zd ZdZdedef fdZ	 ddej                  dej                  dz  dej                  dz  d	e	e
   d
eej                  ej                  f   f
dZd Z xZS )ParakeetEncoderAttentionztMulti-head attention with relative positional encoding. See section 3.3 of https://huggingface.co/papers/1901.02860.r,   	layer_idxc                    t         |   ||       d| _        t        j                  |j
                  |j                  | j                  z  d      | _        t        j                  t        j                  |j                  | j                              | _        t        j                  t        j                  |j                  | j                              | _        y )N)r}   Frf   )r4   r5   	is_causalr   rh   r8   num_attention_headshead_dimrelative_k_proj	Parameterr#   zerosbias_ubias_vr=   r,   r}   r?   s      r(   r5   z!ParakeetEncoderAttention.__init__w   s    95!yy););V=W=WZ^ZgZg=gnstll5;;v/I/I4==#YZll5;;v/I/I4==#YZr'   Nr@   position_embeddingsr   kwargsreturnc           
         |j                   d d }|\  }}||d| j                  f}| j                  |      j                  |      j	                  dd      }	| j                  |      j                  |      j	                  dd      }
| j                  |      j                  |      j	                  dd      }t        j                  | j                  j                  t              }|	| j                  j                  d| j                  j                  d| j                        z   }|	| j                  j                  d| j                  j                  d| j                        z   }| j                  |      }|j                  |d| j                  j                  | j                        }||j!                  dddd      z  }| j#                  |      }|dd |f   }|| j$                  z  }|)|j'                  |j)                         t+        d            } || f||
||| j,                  sdn| j.                  | j$                  d	|\  }} |j0                  g |d j3                         }| j5                  |      }||fS )
NrC   r   r   r   r   .z-inf        )querykeyvaluer   rv   scaling)rL   r   q_projviewrR   k_projv_projr   get_interfacer,   _attn_implementationr   r   r   r   r   permute
_rel_shiftr   masked_fill_logical_notr;   rt   attention_dropoutrV   
contiguouso_proj)r=   r@   r   r   r   input_shape
batch_sizerW   hidden_shapequery_states
key_statesvalue_statesattention_interfacequery_states_with_bias_uquery_states_with_bias_vrelative_key_states	matrix_bdattn_outputattn_weightss                      r(   r]   z ParakeetEncoderAttention.forward   sj    $))#2.!,
J"JDMMB{{=166|DNNqRST[[/44\BLLQPQR
{{=166|DNNqRST(?(M(MKK,,.E)
 $0$++2B2Bt{{..4==3
 $
  $0$++2B2Bt{{..4==3
 $
  #223FG166z2t{{GfGfhlhuhuv -/B/J/J1aQRTU/VV	OOI.	c;J;./	,	% "..~/I/I/KUSY][I %8	%
*$#}}C$2H2HLL	%
 	%
!\ *k));;;;FFHkk+.L((r'   c                     |j                   \  }}}}t        j                  j                  |d      }|j	                  ||d|      }|ddddddf   j	                  ||||      }|S )ztRelative position shift for Shaw et al. style attention. See appendix B of https://huggingface.co/papers/1901.02860.)r   r   )padrC   Nr   )rL   r   ru   r   r   )r=   attention_scoresr   	num_headsquery_lengthposition_lengths         r(   r   z#ParakeetEncoderAttention._rel_shift   st    ?O?U?U<
I|_==,,-=6,J+00YLY+Aq!"H5:::yR^`opr'   r^   )r    r!   r"   r_   r   intr5   r#   r$   r   r   tupler]   r   ra   rb   s   @r(   r|   r|   t   s    ~[4 [ [ /3	7)||7) #\\D07) t+	7)
 +,7) 
u||U\\)	*7)r r'   r|   c                        e Zd Zdef fdZdej                  dej                  fdZ	d	dej                  dej                  fdZ
 xZS )
 ParakeetEncoderSubsamplingConv2Dr,   c                    t         |           |j                  | _        |j                  | _        |j                  | _        | j                  dz
  dz  | _        t        t        j                  |j                              | _        t        j                         | _        | j                   j#                  t        j$                  d| j                  | j                  | j
                  | j                               | j                   j#                  t        j&                                t)        | j                  dz
        D ]  }| j                   j#                  t        j$                  | j                  | j                  | j                  | j
                  | j                  | j                               | j                   j#                  t        j$                  | j                  | j                  d             | j                   j#                  t        j&                                 |j*                  | j
                  | j                  z  z  }t        j,                  |j                  |z  |j.                  d      | _        y )Nr   r   )kernel_sizestridepadding)r   r   r   groupsr   Trf   )r4   r5   subsampling_conv_kernel_sizer   subsampling_conv_strider   subsampling_conv_channelschannelsr   r   mathlog2subsampling_factor
num_layersr   
ModuleListlayersappendConv2dReLUrangenum_mel_binsrh   r8   linear)r=   r,   i
out_lengthr?   s       r(   r5   z)ParakeetEncoderSubsamplingConv2D.__init__   s   !>>4488((1,2dii(A(ABC mmoIIaD4D4DT[[bfbnbno	
 	2779%t*+ 	*AKK		MMMM $ 0 0;; LL==	 KKryySTUVKKrwwy)	*" ((T[[$//-IJ
ii @ @: MvOaOahlmr'   input_lengths
conv_layerc                     t        |d      rR|j                  dk7  rC|j                  }|j                  d   }|j                  d   }||d   z   |d   z   |z
  |z  dz   }|S |S )Nr   )r   r   r   r   )hasattrr   r   r   )r=   r   r   r   r   r   output_lengthss          r(   _get_output_lengthz3ParakeetEncoderSubsamplingConv2D._get_output_length   sx    :x(Z->->&-H ((G$003K&&q)F+gaj871:ESX^^abbN!!r'   input_featuresr   c                    |j                  d      }||j                  d      nd }| j                  D ]  } ||      }t        |t        j
                        s&|)| j                  ||      }|j                  d   }t        j                  ||j                        |d d d f   k  }||d d d d d d f   z  } |j                  dd      j                  |j                  d   |j                  d   d      }| j                  |      }|S )Nr   rC   r   rD   r   )	unsqueezesumr   rO   r   r   r   rL   r#   r7   r2   rR   rV   r   )r=   r   r   r@   current_lengthslayercurrent_seq_lengthchannel_masks           r(   r]   z(ParakeetEncoderSubsamplingConv2D.forward   s   &0034B4N.,,R0TX[[ 
	@E!-0M %+0J"&"9"9/5"Q%2%8%8%;"LL!3N<Q<QRUdefhlelUmm  aq$.>!??
	@ &//15==m>Q>QRS>TVcViVijkVlnpqM2r'   r^   )r    r!   r"   r   r5   r#   r$   r   r   r   r]   ra   rb   s   @r(   r   r      sI    !n4 !nF	 	")) 	ell ELL r'   r   c                        e Zd Zddededz  f fdZ	 	 ddej                  dej                  dz  dej                  dz  dee	   d	ej                  f
d
Z
 xZS )ParakeetEncoderBlockNr,   r}   c                    t         |           d| _        t        |      | _        t        ||      | _        t        |      | _        t        |      | _	        t        j                  |j                        | _        t        j                  |j                        | _        t        j                  |j                        | _        t        j                  |j                        | _        t        j                  |j                        | _        y NF)r4   r5   gradient_checkpointingrd   feed_forward1r|   	self_attnrx   convfeed_forward2r   	LayerNormr8   norm_feed_forward1norm_self_att	norm_convnorm_feed_forward2norm_outr   s      r(   r5   zParakeetEncoderBlock.__init__	  s    &+#7?1&)D4V<	7?"$,,v/A/A"B\\&*<*<=f&8&89"$,,v/A/A"BV%7%78r'   r@   r   r   r   r   c                 x   |}| j                  | j                  |            }|d|z  z   }| j                  |      } | j                  d|||d|\  }}||z   }| j	                  | j                  |      |      }	||	z   }| j                  | j                  |            }
|d|
z  z   }| j                  |      }|S )Ng      ?)r@   r   r   )r   r&   )	r   r   r   r   r   r   r   r   r   )r=   r@   r   r   r   residualnormalized_hidden_statesr   _conv_output
ff2_outputs              r(   r]   zParakeetEncoderBlock.forward  s     !**4+B+B=+QR 3#66#'#5#5m#D ' 
2) 3
 	
Q &3ii} =ni]%3''(?(?(NO
%j(88m4r'   r^   NN)r    r!   r"   r   r   r5   r#   r$   r   r   r]   ra   rb   s   @r(   r   r     sx    94 9t 9$ /337	|| t+ #\\D0	
 +, 
r'   r   c                        e Zd ZU eed<   dZdZdZdZdgZ	dZ
dZdZdZdZdZeedZ ej(                          fd	       Zd
ej,                  fdZddej,                  dedz  fdZ xZS )ParakeetPreTrainedModelr,   modelr   audioTr   F)r@   
attentionsc                    t         |   |       t        | j                  d      r| j                  j                  }n%t        | j                  j                         dd      }t        |t              rEt        j                  |j                  d|       t        j                  |j                  d|       y t        |t              ryddt        j                  d| j                  j                   dt        j"                  	      | j                  j                   z  z  z  }t        j$                  |j&                  |       y y )
Ninitializer_rangeg{Gz?r   )meanstdr/   r.   r   r   r0   )r4   _init_weightsr   r,   r   getattrget_text_configrO   r|   initnormal_r   r   r*   r#   r7   r8   r9   copy_r+   )r=   moduler   r+   r?   s       r(   r   z%ParakeetPreTrainedModel._init_weightsM  s    f%4;; 34++//C $++5579LdSCf67LLSc:LLSc: DEELLDKK,C,CQekkZ]a]h]h]t]ttuH JJv1	 Fr'   r   c                    t        | j                  t              r| j                  j                  n| j                  }|j                  }|j
                  }t        t        j                  |j                              }|dz
  dz  dz  }||z
  }|}t        |      D ]Q  }	t        j                  |j                  t        j                        |z   |      dz   }t        j                  |      }S |j                  t        j                        S )Nr   r   r0   r/   )rO   r,   r   encoder_configr   r   r   r   r   r   r   r#   divr:   r;   floor)
r=   r   r  r   r   r   all_paddingsadd_padlengthsr   s
             r(   _get_subsampling_output_lengthz6ParakeetPreTrainedModel._get_subsampling_output_lengtha  s    7A$++O`7a33gkgrgr$AA77>#D#DEF
#aA-1,z" 	+Aii


 = GPSVVGkk'*G	+ zz		z**r'   Nr   target_lengthc                     | j                  |j                  d            }||n|j                         }t        j                  ||j
                        |dddf   k  }|S )z
        Convert the input attention mask to its subsampled form. `target_length` sets the desired output length, useful
        when the attention mask length differs from `sum(-1).max()` (i.e., when the longest sequence in the batch is padded)
        rC   NrD   )r  r   maxr#   r7   r2   )r=   r   r	  r   
max_lengths        r(   _get_output_attention_maskz2ParakeetPreTrainedModel._get_output_attention_maskr  sc    
 <<^=O=OPR=ST&3&?]^EWEWEY
j9N9NOR`abdhahRiir'   r^   )r    r!   r"   r   r%   base_model_prefixmain_input_nameinput_modalitiessupports_gradient_checkpointing_no_split_modules_supports_flat_attention_mask_supports_sdpa_supports_flex_attn_supports_flash_attn_can_compile_fullgraph_supports_attention_backendr   r|   _can_record_outputsr#   r`   r   r$   r  r   r  ra   rb   s   @r(   r   r   7  s    &O&*#/0$(!N !!"&-.
 U]]_2 2&+ELL +"	 	VY\`V` 	r'   r   z{
    The Parakeet Encoder model, based on the [Fast Conformer architecture](https://huggingface.co/papers/2305.05084).
    c                        e Zd ZU eed<   dZdef fdZeee		 	 dde
j                  de
j                  dz  dedz  dee   d	ef
d
                     Z xZS )ParakeetEncoderr,   encoderc           	         t         |   |       || _        d| _        |j                  | _        |j
                  | _        |j                  | _        |j                  rt        j                  |j                        nd| _        t        |      | _        t        |      | _        t!        j"                  t%        |j&                        D cg c]  }t)        ||       c}      | _        | j-                          y c c}w )NFr/   )r4   r5   r,   r   rv   dropout_positions	layerdropscale_inputr   sqrtr8   input_scaler   subsamplingr*   encode_positionsr   r   r   num_hidden_layersr   r   	post_initr   s      r(   r5   zParakeetEncoder.__init__  s     &+#~~!'!9!9))<B<N<N499V%7%78TW;FC DV LmmFKFLdLdFef!&)4f
 	 gs   
C:Nr   r   output_attention_maskr   r   c                    | j                  ||      }|| j                  z  }| j                  |      }t        j                  j                  || j
                  | j                        }t        j                  j                  || j                  | j                        }|u| j                  ||j                  d         }|j                  d      j                  d|j                  d   d      }||j                  dd      z  }|j                  d      }| j                  D ]E  }d}	| j                  r&t        j                  g       }
|
| j                   k  rd}	|	r: ||f||d	|}G t#        ||rj%                         
      S d
      S )aJ  
        output_attention_mask (`bool`, *optional*):
            Whether to return the output attention mask.

        Example:

        ```python
        >>> from transformers import AutoProcessor, ParakeetEncoder
        >>> from datasets import load_dataset, Audio

        >>> model_id = "nvidia/parakeet-ctc-1.1b"
        >>> processor = AutoProcessor.from_pretrained(model_id)
        >>> encoder = ParakeetEncoder.from_pretrained(model_id)

        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
        >>> ds = ds.cast_column("audio", Audio(sampling_rate=processor.feature_extractor.sampling_rate))

        >>> inputs = processor(ds[0]["audio"]["array"])
        >>> encoder_outputs = encoder(**inputs)

        >>> print(encoder_outputs.last_hidden_state.shape)
        ```
        rr   Nr   r	  rC   r   FT)r   r   )last_hidden_stater   )r#  r"  r$  r   ru   rv   rt   r  r  rL   r   rN   rR   r   r#   randr  r   r   )r=   r   r   r'  r   r@   r   output_maskencoder_layerto_dropdropout_probabilitys              r(   r]   zParakeetEncoder.forward  s   D ((H%(8(88"33MB--mt||VZVcVc-d mm334#9#9DMM 4 
 %99.XeXkXklmXn9oK(2215<<RATATUVAWY[\N+n.F.Fq!.LLN+55a8N![[ 	MG}}&+jjn#&7"G -!!#1(;! 	!	  *+QfKOO<M
 	
lp
 	
r'   r   )r    r!   r"   r   r%   r  r5   r   r   r   r#   r$   boolr   r   r
   r]   ra   rb   s   @r(   r  r  ~  s     "!!4 &  /3-1	@
@
 t+@
  $d{	@

 +,@
 
@
   @
r'   r  c                       e Zd ZU dZej
                  ed<   dZeej                     dz  ed<   dZ
eeej                        dz  ed<   dZeeej                        dz  ed<   y)ParakeetGenerateOutputal  
    Outputs of Parakeet models.

    Args:
        sequences (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
            The generated sequences. The second dimension (sequence_length) is either equal to `max_length` or shorter
            if all batches finished early due to the `eos_token_id`.
        logits (`tuple(torch.FloatTensor)` *optional*, returned when `output_logits=True`):
            Unprocessed prediction scores of the language modeling head (scores for each vocabulary token before SoftMax)
            at each generation step. Tuple of `torch.FloatTensor` with up to `max_new_tokens` elements (one element for
            each generated token), with each tensor of shape `(batch_size, config.vocab_size)`.
        attentions (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `output_attentions=True`):
            Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of
            `torch.FloatTensor` of shape `(batch_size, num_heads, generated_length, sequence_length)`.
        hidden_states (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `output_hidden_states=True`):
            Tuple (one element for each generated token) of tuples (one element for each layer of the decoder) of
            `torch.FloatTensor` of shape `(batch_size, generated_length, hidden_size)`.
    	sequencesNlogitsr   r@   )r    r!   r"   r_   r#   
LongTensorr%   r4  r   FloatTensorr   r@   r&   r'   r(   r2  r2    sm    & .2FE%##$t+29=JeE--./$6=<@M5u0012T9@r'   r2  zS
    Parakeet Encoder with a Connectionist Temporal Classification (CTC) head.
    c                   L    e Zd ZU eed<   def fdZee	 	 ddej                  dej                  dz  dej                  dz  de
e   def
d	              Z ej                         	 	 ddej                  dej                  dz  d
ede
e   deej"                  z  f
d       Z xZS )ParakeetForCTCr,   c                     t         |   |       t        |j                        | _        t        j                  |j                  j                  |j                  d      | _	        | j                          y )Nr   r   )r4   r5   r  r  r  r   Conv1dr8   
vocab_sizectc_headr&  rp   s     r(   r5   zParakeetForCTC.__init__  sS     &v'<'<=		&"7"7"C"CVEVEVdefr'   Nr   r   labelsr   r   c           
          | j                   d||d|}|j                  }| j                  |j                  dd            j                  dd      }d}|Y||n$t	        j
                  |t        j                        }| j                  |j                  d            }	|| j                  j                  k7  }
|
j                  d      }|j                  |
      }t        j                  j                  |dt        j                        j                  dd      }t        j                   j"                  j%                  d	
      5  t        j                  j'                  |||	|| j                  j                  | j                  j(                  | j                  j*                        }ddd       t-        |||j.                  |j0                        S # 1 sw Y   ,xY w)a  
        Example:

        ```python
        >>> from transformers import AutoProcessor, ParakeetForCTC
        >>> from datasets import load_dataset, Audio

        >>> model_id = "nvidia/parakeet-ctc-1.1b"
        >>> processor = AutoProcessor.from_pretrained(model_id)
        >>> model = ParakeetForCTC.from_pretrained(model_id)

        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
        >>> ds = ds.cast_column("audio", Audio(sampling_rate=processor.feature_extractor.sampling_rate))

        >>> inputs = processor(ds[0]["audio"]["array"], text=ds[0]["text"])
        >>> outputs = model(**inputs)

        >>> print(outputs.loss)
        ```r   r   r   r   Nr0   rC   )rJ   r1   r   F)rH   )blank	reductionzero_infinity)lossr4  r@   r   r&   )r  r*  r<  rR   r#   	ones_likelongr  r   r,   pad_token_idmasked_selectr   ru   log_softmaxfloat32backendscudnnflagsctc_lossctc_loss_reductionctc_zero_infinityr   r@   r   )r=   r   r   r=  r   encoder_outputsr@   r4  rC  r   labels_masktarget_lengthsflattened_targets	log_probss                 r(   r]   zParakeetForCTC.forward  s   : '$,, 
))
 
 (99}66q!<=GG1M #1"<%//R`hmhrhrBs  !??@R@RSU@VWM !DKK$<$<<K(__R0N & 4 4[ A 11&b1V``abdefI%%++E+: 	}}--%!"++22"kk<<"&++"?"? . 	 )77&11	
 	
	 	s   A#GGreturn_dict_in_generatec                 H   d|d<    | j                   d	||d|}|j                  j                  d      }|:| j                  ||j                  d         }| j
                  j                  || <   |r-t        ||j                  |j                  |j                        S |S )
a3  
        Example:

        ```python
        >>> from transformers import AutoProcessor, ParakeetForCTC
        >>> from datasets import load_dataset, Audio

        >>> model_id = "nvidia/parakeet-ctc-1.1b"
        >>> processor = AutoProcessor.from_pretrained(model_id)
        >>> model = ParakeetForCTC.from_pretrained(model_id)

        >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
        >>> ds = ds.cast_column("audio", Audio(sampling_rate=processor.feature_extractor.sampling_rate))

        >>> inputs = processor(ds[0]["audio"]["array"], text=ds[0]["text"])
        >>> predicted_ids = model.generate(**inputs)
        >>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)

        >>> print(transcription)
        ```
        Treturn_dictr?  rC   rI   r   r)  )r3  r4  r   r@   r&   )
r]   r4  argmaxr  rL   r,   rF  r2  r   r@   )r=   r   r   rU  r   outputsr3  s          r(   generatezParakeetForCTC.generateT  s    : !%}".$,, #
))#
 #
 NN))b)1	 %!<<^[d[j[jkl[m<nN)-)A)AI~o&")#~~"--%33	  r'   r   r   )r    r!   r"   r   r%   r5   r   r   r#   r$   r   r   r   r]   r`   r0  r2  r5  rZ  ra   rb   s   @r(   r8  r8    s    0   /3&*	E
E
 t+E
 t#	E

 +,E
 
E
  E
N U]]_ /3(-	33 t+3 "&	3
 +,3 
 %"2"2	23 3r'   r8  )r8  r  r   )4r_   r   collections.abcr   dataclassesr   r#   r    r   r   activationsr   modeling_layersr	   modeling_outputsr
   r   modeling_utilsr   r   processing_utilsr   utilsr   r   r   r   utils.genericr   r   4fastspeech2_conformer.modeling_fastspeech2_conformerr   llama.modeling_llamar   r   configuration_parakeetr   r   r   Moduler*   rd   rx   r|   r   r   r   r  r2  r8  __all__r&   r'   r(   <module>rj     sa     $ !   & ! 9 ? F & V V ? h J L 
/ / //7299 /7d 0'L 0
L ~ L ^Bryy BJ,5 ,^ Co C CL 
Z
- Z

Z
z A[ A A4 
H, H
HV Kr'   