§
    9²¸j¬L  ã                   óD  — d dl Zd dlmZ ddlmZmZ ddlmZ ddl	m
Z
 ddlmZ ddlmZmZmZmZmZmZmZ dd	lmZ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!  e¦   «         rd dl"Z"d dl#m$c m%Z&  e¦   «         rd dl'Z' ej(        e)¦  «        Z* ed¬¦  «        e G d„ de¦  «        ¦   «         ¦   «         Z+ G d„ de ¦  «        Z, G d„ de¦  «        Z- G d„ de¦  «        Z. G d„ de!¦  «        Z/ ed¬¦  «         G d„ de¦  «        ¦   «         Z0 G d„ de¦  «        Z1g d ¢Z2dS )!é    N)Ústricté   )Ú
AudioInputÚmake_list_of_audio)ÚBatchFeature)Úcreate_bidirectional_mask)ÚUnpack)ÚPaddingStrategyÚ
TensorTypeÚTransformersKwargsÚauto_docstringÚcan_return_tupleÚis_torch_availableÚlogging)Úis_torchaudio_availableÚrequiresé   )ÚXcodec2Config)ÚXcodec2FeatureExtractor)ÚXcodec2DecoderOutputÚXcodec2EncoderOutputÚXcodec2ModelÚXcodec2OutputÚXcodec2PreTrainedModelzneuphonic/neucodec)Ú
checkpointc                   ó€   — e Zd ZU dZdZdZeed<   dZeed<    e	¦   «         Z
edefd„¦   «         Zedefd	„¦   «         Zd
S )ÚNeuCodecConfigaÉ  
    downsampling_ratios (`list[int]`, *optional*, defaults to `[2, 2, 4, 4, 5]`):
        Ratios for downsampling in the encoder.
    semantic_model_config (`Union[Dict, Wav2Vec2BertConfig]`, *optional*):
        An instance of the configuration object for the semantic (Wav2Vec2BertConfig) model.
    quantization_dim (`int`, *optional*, defaults to 2048):
        Dimension for the vector quantization codebook.
    quantization_levels (`list[int]`, *optional*, defaults to `[4, 4, 4, 4, 4, 4, 4, 4]`):
        Levels for the vector quantization codebook.
    input_sampling_rate (`int`, *optional*, defaults to 16000):
        Sampling rate, in hertz (Hz), of the encoder's input audio waveform.
    output_sampling_rate (`int`, *optional*, defaults to 24000):
        Sampling rate, in hertz (Hz), of the decoder's output audio waveform.

    Example:

    ```python
    >>> from transformers import NeuCodecConfig, NeuCodecModel

    >>> # Initializing configuration
    >>> configuration = NeuCodecConfig()

    >>> # Initializing a model (with random weights) from the configuration
    >>> model = NeuCodecModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```Úneucodeci€>  Úinput_sampling_rateiÀ]  Úoutput_sampling_rateÚreturnc                 óN   — t          t          j        | j        ¦  «        ¦  «        S )zhHop length, in samples at `input_sampling_rate`, between successive codes (i.e. the encoder frame rate).)ÚintÚnpÚprodÚdownsampling_ratios©Úselfs    ú}/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/transformers/models/neucodec/modular_neucodec.pyÚencoder_hop_lengthz!NeuCodecConfig.encoder_hop_length[   s   € õ •2”7˜4Ô3Ñ4Ô4Ñ5Ô5Ð5ó    c                 óJ   — t          | j        | j        z  | j        z  ¦  «        S ©N)r#   r*   r    r   r'   s    r)   Ú
hop_lengthzNeuCodecConfig.hop_length`   s%   € õ �4Ô*¨TÔ-FÑFÈÔIaÑaÑbÔbÐbr+   N)Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typer   r#   Ú__annotations__r    ÚAttributeErrorÚsampling_rateÚpropertyr*   r.   © r+   r)   r   r   6   s©   € € € € € € ðð ð: €JØ%Ð˜Ð%Ð%Ñ%Ø &Ð˜#Ð&Ð&Ñ&Ø"�NÑ$Ô$€Màð6 Cð 6ð 6ð 6ñ „Xð6ð ðc˜Cð cð cð cñ „Xðcð cð cr+   r   c                   ó   — e Zd ZdS )ÚNeuCodecOutputN©r/   r0   r1   r8   r+   r)   r:   r:   g   ó   € € € € € Ø€Dr+   r:   c                   ó   — e Zd ZdS )ÚNeuCodecEncoderOutputNr;   r8   r+   r)   r>   r>   k   r<   r+   r>   c                   ó   — e Zd ZdS )ÚNeuCodecDecoderOutputNr;   r8   r+   r)   r@   r@   o   r<   r+   r@   c                   ó   — e Zd ZdS )ÚNeuCodecPreTrainedModelNr;   r8   r+   r)   rB   rB   s   r<   r+   rB   z"NeuCodec neural audio codec model.)Úcustom_introc                   óÎ  ‡ — e Zd Zdefˆ fd„Zee	 	 	 ddej        dej        dej        dz  dej        dz  d	e	d
e
e         deez  f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ee	 	 	 ddej        dej        dej        dz  dej        dz  d	e	d
e
e         deez  fd„¦   «         ¦   «         Zˆ xZS )ÚNeuCodecModelÚconfigc                 óŠ   •— t          ¦   «                              |¦  «         |j        | _        |j        |j        z  | _        d S r-   )ÚsuperÚ__init__r*   r.   r    r   Úsample_rate_conversion_factor)r(   rF   Ú	__class__s     €r)   rI   zNeuCodecModel.__init__y   s@   ø€ Ý‰Œ×Ò˜Ñ Ô Ð ð !Ô3ˆŒØ-3Ô-HÈ6ÔKeÑ-eˆÔ*Ð*Ð*r+   NFÚinput_valuesÚinput_featuresÚpadding_maskÚinput_features_maskÚoutput_latentsÚkwargsr!   c                 óÐ  — t          j        ¦   «         5  |                      ||¬¦  «        }ddd¦  «         n# 1 swxY w Y   |j                             dd¦  «        }|                      |¦  «        }|                      |¦  «        }	t          |	j        d         |j        d         ¦  «        }
|	dd|
…f         }	|dd|
…f         }t          j	        ||	gd¬¦  «        }|  
                    |                     dd¦  «        ¦  «        }|                      |¦  «        \  }}|                     dd¦  «        }|                     dd¦  «        }d}|�ƒ|                     dd¬	¦  «        }|| j        z  }|| j        z  }t          j        |j        d         |j        ¬
¦  «                             dd¦  «        }||k                          |j        ¦  «        }t)          ||r|nd|¬¦  «        S )a  
        input_values (`torch.Tensor` of shape `(batch_size, 1, sequence_length)`):
            Input audio waveform.
        input_features (`torch.Tensor` of shape `(batch_size, mel_bins, time_steps)`):
            Input audio mel spectrogram for semantic encoding.
        padding_mask (`torch.Tensor` of shape `(batch_size, 1, sequence_length)`):
            Padding mask used to pad `input_values`.
        input_features_mask (`torch.Tensor` of shape `(batch_size, time_steps)`, *optional*):
            Attention mask for the spectrogram input to the semantic encoder. `1` for valid frames, `0` for padding.
        output_latents (`bool`, *optional*, defaults to `False`):
            Whether to return the continuous latent representation from the quantizer.
        )Úattention_maskNé   r   éÿÿÿÿ.©ÚdimT)rW   Úkeepdim)Údevice)Úaudio_codesÚlatentsÚaudio_codes_mask)ÚtorchÚno_gradÚsemantic_encoderÚlast_hidden_stateÚ	transposeÚsemantic_adapterÚacoustic_encoderÚminÚshapeÚcatÚ
fc_encoderÚ	quantizerÚsumrJ   r.   ÚarangerY   ÚviewÚtoÚdtyper>   )r(   rL   rM   rN   rO   rP   rQ   Úsemantic_outputÚsemantic_hidden_statesÚacoustic_hidden_statesÚ
min_lengthÚhidden_statesr[   rZ   r\   Úaudio_lengthÚtoken_lengthÚidxs                     r)   ÚencodezNeuCodecModel.encode�   sT  € õ2 Œ]‰_Œ_ð 	hð 	hØ"×3Ò3°NÐSfÐ3ÑgÔgˆOð	hð 	hð 	hñ 	hô 	hð 	hð 	hð 	hð 	hð 	hð 	høøøð 	hð 	hð 	hð 	hà!0Ô!B×!LÒ!LÈQÐPQÑ!RÔ!RÐØ!%×!6Ò!6Ð7MÑ!NÔ!NÐð "&×!6Ò!6°|Ñ!DÔ!DÐõ Ð/Ô5°bÔ9Ð;QÔ;WÐXZÔ;[Ñ\Ô\ˆ
Ø!7¸¸[¸j¸[Ð8HÔ!IÐØ!7¸¸[¸j¸[Ð8HÔ!IÐåœ	Ð#9Ð;QÐ"RÐXYÐZÑZÔZˆØŸš¨×(?Ò(?ÀÀ1Ñ(EÔ(EÑFÔFˆð  $Ÿ~š~¨mÑ<Ô<Ñˆ�Ø×#Ò# A qÑ)Ô)ˆØ!×+Ò+¨A¨qÑ1Ô1ˆð  ÐØÐ#Ø'×+Ò+°¸DÐ+ÑAÔAˆLØ'¨$Ô*LÑLˆLØ'¨4¬?Ñ:ˆLÝ”,˜{Ô0°Ô4¸\Ô=PÐQÑQÔQ×VÒVÐWXÐZ\Ñ]Ô]ˆCØ # lÒ 2×6Ò6°|Ô7IÑJÔJÐå$Ø#Ø-Ð7�G�G°4Ø-ð
ñ 
ô 
ð 	
s   ”8¸<¿<rZ   r[   r\   c                 ó$  — |€|€t          d¦  «        ‚|�/| j                             |                     dd¦  «        ¦  «        }n|                     dd¦  «        }t	          | j        ||¬¦  «        } | j        |fd|i|¤Ž}t          |¬¦  «        S )a1  
        audio_codes (`torch.LongTensor`  of shape `(batch_size, 1, codes_length)`):
            Discrete code indices computed using `model.encode`.
        latents (torch.Tensor of shape `(batch_size, dimension, time_steps)`, *optional*):
            Quantized continuous representation of input.
        audio_codes_mask (`torch.Tensor` of shape `(batch_size, codes_length)`, *optional*):
            Mask marking valid (non-padding) positions, as returned by `model.encode`. Needed for correct
            batched decoding of variable-length audio.
        Nz3Either `latents` or `audio_codes` must be provided.rT   r   )rF   Úinputs_embedsrS   rS   )Úaudio_values)Ú
ValueErrorrh   Ú
from_codesra   r   rF   Úacoustic_decoderr@   )r(   rZ   r[   r\   rQ   rS   Úrecon_audios          r)   ÚdecodezNeuCodecModel.decode¿   s³   € ð$ ˆ?˜{Ð2ÝÐRÑSÔSÐSàÐ"Ø”n×/Ò/°×0EÒ0EÀaÈÑ0KÔ0KÑLÔLˆGˆGà×'Ò'¨¨1Ñ-Ô-ˆGõ 3Ø”;Ø!Ø+ð
ñ 
ô 
ˆð ,�dÔ+¨GÐ]Ð]ÀNÐ]ÐV\Ð]Ð]ˆÝ$°+Ð>Ñ>Ô>Ð>r+   c                 ó"  — |j         d         }t          || j        z  ¦  «        }|                      ||||dd¬¦  «        }	 | j        d	|	j        |	j        ddœ|¤Žd         dd|…f         }
t          |
|	j        |r|	j        nd|	j        ¬¦  «        S )
aC  
        input_values (`torch.Tensor` of shape `(batch_size, 1, sequence_length)`):
            Input audio waveform, sampled at `config.input_sampling_rate`.
        input_features (`torch.Tensor` of shape `(batch_size, mel_bins, time_steps)`):
            Input audio mel spectrogram for semantic encoding.
        padding_mask (`torch.Tensor` of shape `(batch_size, 1, sequence_length)`):
            Padding mask used to pad `input_values`.
        input_features_mask (`torch.Tensor` of shape `(batch_size, time_steps)`, *optional*):
            Attention mask for the spectrogram input to the semantic encoder. `1` for valid frames, `0` for padding.
        output_latents (`bool`, *optional*, defaults to `False`):
            Whether to return the continuous latent representation from the quantizer.

        Examples:

        ```python
        >>> from datasets import load_dataset
        >>> from transformers import AutoFeatureExtractor, NeuCodecModel

        >>> dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
        >>> audio = dataset["train"]["audio"][0]["array"]

        >>> model_id = "neuphonic/neucodec"
        >>> model = NeuCodecModel.from_pretrained(model_id)
        >>> feature_extractor = AutoFeatureExtractor.from_pretrained(model_id)

        >>> inputs = feature_extractor(audio=audio, sampling_rate=feature_extractor.sampling_rate, return_tensors="pt")

        >>> outputs = model(**inputs)
        >>> audio_codes = outputs.audio_codes
        >>> audio_values = outputs.audio_values  # sampled at 24kHz
        ```rU   T)rM   rN   rO   rP   Úreturn_dict)r[   r\   r€   r   .N)ry   rZ   r[   r\   r8   )	re   r#   rJ   rv   r~   r[   r\   r:   rZ   )r(   rL   rM   rN   rO   rP   rQ   Úinput_lengthÚoutput_lengthÚencoder_outputsry   s              r)   ÚforwardzNeuCodecModel.forwardã   sÞ   € ðV $Ô)¨"Ô-ˆÝ˜L¨4Ô+MÑMÑNÔNˆàŸ+š+ØØ)Ø%Ø 3ØØð &ñ 
ô 
ˆð #�t”{ð 
Ø#Ô+Ø,Ô=Øð
ð 
ð ð	
ð 
ð
 ôð
 �.�=�.Ð ô"ˆõ Ø%Ø'Ô3Ø/=ÐG�OÔ+Ð+À4Ø,Ô=ð	
ñ 
ô 
ð 	
r+   )NNF)NNN)r/   r0   r1   r   rI   r   r   r]   ÚTensorÚboolr	   r   Útupler>   rv   r@   r~   r:   r„   Ú__classcell__)rK   s   @r)   rE   rE   w   s"  ø€ € € € € ðf˜~ð fð fð fð fð fð fð Øð
 -1Ø37Ø$ð:
ð :
à”lð:
ð œð:
ð ”l TÑ)ð	:
ð
 #œ\¨DÑ0ð:
ð ð:
ð Ð+Ô,ð:
ð 
Ð&Ñ	&ð:
ð :
ð :
ñ Ôñ „^ð:
ðx Øð ,0Ø'+Ø04ð	 ?ð  ?à”\ DÑ(ð ?ð ” Ñ$ð ?ð  œ,¨Ñ-ð	 ?ð
 Ð+Ô,ð ?ð 
Ð&Ñ	&ð ?ð  ?ð  ?ñ Ôñ „^ð ?ðD Øð
 -1Ø37Ø$ð@
ð @
à”lð@
ð œð@
ð ”l TÑ)ð	@
ð
 #œ\¨DÑ0ð@
ð ð@
ð Ð+Ô,ð@
ð 
�Ñ	ð@
ð @
ð @
ñ Ôñ „^ð@
ð @
ð @
ð @
ð @
r+   rE   c                   óŒ   — e Zd Z ed¬¦  «        	 	 	 	 	 	 ddedeez  ez  d	edz  d
edee	z  dz  dedz  dede
fd„¦   «         ZdS )ÚNeuCodecFeatureExtractor)r]   Ú
torchaudio)ÚbackendsTNFÚcpuÚaudioÚpaddingÚ
max_lengthÚ
truncationÚreturn_tensorsr6   rY   r!   c                 óŠ  — |�2|| j         k    r&t          d| › d| j         › d| j         › d|› d�	¦  «        ‚n(t                               d| j        j        › d�¦  «         t          |¦  «        }|D ]$}	|	j        d	k    rt          d
|	j        › �¦  «        ‚Œ%t          |¦  «        }
d„ |D ¦   «         }| j
                             t          d|i¦  «        ||||| j        d¬¦  «        }|                     d¦  «        }|d         dd…ddd…f         }g }t          |
¦  «        D �]}| j
                             t          d||         gi¦  «        | j        d¬¦  «        }|d                              |¦  «        }t"          j        j                             |dz  | j        | j        | j         z  dz  | j        | j         z  dz  | j         dddddddd| j         d	z  ¬¦  «        }||                     d¦  «        z
  t3          j        |                     dd¬¦  «        dz   ¦  «        z  }|                     |¦  «         �Œt          d|i¦  «        }|                      ||||| j        |d¬¦  «        }|d         }|                     d¦  «        }|j        d         |j        d         | j        z  z
  }|dd…d|…dd…f                              |
|| j        z  | j        | j        z  ¦  «        }|�I|dd…d|…f                              |
|| j        z  | j        ¦  «                              d ¬!¦  «        j!        }t          ||||d"œ|¬#¦  «        S )$aÄ  
        Args:
            audio (`np.ndarray`, `torch.Tensor`, `list[np.ndarray]`, `list[torch.Tensor]`):
                Numpy array or torch tensor with shape (num_channels, sequence_length). A list of such arrays or
                tensors can also be provided for a batch of inputs.
            padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`):
                Select a strategy to pad the returned sequences (according to the model's padding side and padding
                index) among:

                - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
                  sequence if provided).
                - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
                  acceptable input length for the model if that argument is not provided.
                - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
                  lengths).
            max_length (`int`, *optional*):
                Maximum length of the returned list and optionally padding length (see above).
            truncation (`bool`):
                Activates truncation to cut input sequences longer than *max_length* to *max_length*.
            return_tensors (`str` or [`~utils.TensorType`], *optional*):
                If set, will return tensors instead of list of python integers. Acceptable values are:

                - `'tf'`: Return TensorFlow `tf.constant` objects.
                - `'pt'`: Return PyTorch `torch.Tensor` objects.
                - `'np'`: Return Numpy `np.ndarray` objects.
            sampling_rate (`int`, *optional*):
                The sample rate at which the `audio` input was sampled. It is strongly recommended to pass
                `sampling_rate` at the forward call to prevent silent errors.
            device (`str`, *optional*, defaults to `"cpu"`):
                Device for PyTorch tensors during mel-filter bank feature extraction.
            kwargs (*optional*):
                Remaining dictionary of keyword arguments that will be passed to the tokenizer or the feature
                extractor.
        Nz3The model corresponding to this feature extractor: z& was trained using a sampling rate of zD. Please make sure that the provided `audio` input was sampled with z	 and not ú.zDIt is strongly recommended to pass the `sampling_rate` argument to `zN()`. Failing to do so can result in silent errors that might be hard to debug.r   z6Expected input shape (channels, length) but got shape c                 ó`   — g | ]+}t          j        t          j        |¦  «        d d¬¦  «        ‘Œ,S ))r   rT   ç        )Úvalue)ÚFÚpadr]   Ú	as_tensor)Ú.0Úas     r)   ú
<listcomp>z5NeuCodecFeatureExtractor.__call__.<locals>.<listcomp>l  s3   € ÐMÐMÐMÀ!•”•u” qÑ)Ô)¨6¸Ð=Ñ=Ô=ÐMÐMÐMr+   rŽ   Úpt)r�   r‘   r�   Úreturn_attention_maskÚpad_to_multiple_ofr’   rS   )r    r’   i €  iè  Úpoveyg
×£p=
ï?TFr–   é   )Únum_mel_binsÚframe_lengthÚframe_shiftÚsample_frequencyÚwindow_typeÚpreemphasis_coefficientÚremove_dc_offsetÚuse_log_fbankÚ
use_energyÚditherÚ
snip_edgesÚlow_freqÚ	high_freqr   )ÚunbiasedgH¯¼šò×z>rM   )r�   r�   r‘   r    rŸ   r’   rT   rU   rV   )rL   rN   rM   rO   )Útensor_type)"r6   rz   ÚloggerÚwarningrK   r/   r   Úndimre   ÚlenÚacoustic_encoder_padderr™   r   r.   ÚpopÚrangerl   r‹   Ú
complianceÚkaldiÚfbankr£   r¤   r¥   Úmeanr]   ÚsqrtÚvarÚappendÚstrideÚgetÚreshaperd   Úvalues)r(   rŽ   r�   r�   r‘   r’   r6   rY   rQ   ÚexampleÚ
batch_sizeÚpadded_inputsrN   Úpadded_audioÚmel_featuresÚiÚsingle_padded_audioÚwaveformÚfeaturesÚencoded_inputsÚ
padded_melÚaudio_spectrogramÚspectrogram_maskÚtrimmed_framess                           r)   Ú__call__z!NeuCodecFeatureExtractor.__call__)  s,  € ð^ Ð$Ø Ô 2Ò2Ð2Ý ðFÈ$ð Fð FØÔ*ðFð FàÔ*ðFð Fà5BðFð Fð Fñô ð ð 3õ �NŠNð\ÐW[ÔWeÔWnð \ð \ð \ñô ð õ
 # 5Ñ)Ô)ˆØð 	kð 	kˆGØŒ|˜aÒÐÝ Ð!iÐZaÔZgÐ!iÐ!iÑjÔjÐjð  å˜‘Z”Zˆ
ð NÐMÀuÐMÑMÔMˆØÔ4×8Ò8Ý˜' 5Ð)Ñ*Ô*Ø!Ø!ØØ")Ø#œØð 9ñ 
ô 
ˆð %×(Ò(Ð)9Ñ:Ô:ˆØ$ WÔ-¨a¨a¨a°°q°q°q¨jÔ9ˆð ˆÝ�zÑ"Ô"ð 	*ñ 	*ˆAØ"&Ô">×"BÒ"BÝ˜g¨¨a¬ zÐ2Ñ3Ô3Ø#'¤?Ø#ð #Cñ #ô #Ðð
 +¨7Ô3×6Ò6°vÑ>Ô>ˆHÝ!Ô,Ô2×8Ò8Ø˜EÑ"Ø!Ô.Ø!Ô.°Ô1CÑCÀdÑJØ Ô,¨tÔ/AÑAÀDÑHØ!%Ô!3Ø#Ø(,Ø!%Ø"Ø ØØØØÔ,°Ñ1ð 9ñ ô ˆHð  ! 8§=¢=°Ñ#3Ô#3Ñ3µu´zÀ(Ç,Â,ÈqÐ[_À,ÑB`ÔB`ÐcgÑBgÑ7hÔ7hÑhˆHØ×Ò Ñ)Ô)Ð)Ñ)Ý%Ð'7¸Ð&FÑGÔGˆØ—X’XØØØ!Ø!Ø#œ{Ø")Øð ñ 
ô 
ˆ
ð 'Ð'7Ô8ÐØ%Ÿ>š>Ð*:Ñ;Ô;ÐØ*Ô0°Ô3Ð7HÔ7NÈqÔ7QÐTXÔT_Ñ7_Ñ`ˆØ-¨a¨a¨a°°.°À!À!À!Ð.CÔD×LÒLØ˜¨$¬+Ñ5°tÔ7HÈ4Ì;Ñ7Vñ
ô 
Ðð Ð'à     O ^ OÐ!3Ô4ß’˜ ^°t´{Ñ%BÀDÄKÑPÔPß’˜�‘”Üð	 õ à ,Ø ,Ø"3Ø'7ð	ð ð 'ð
ñ 
ô 
ð 	
r+   )TNFNNr�   )r/   r0   r1   r   r   r†   Ústrr
   r#   r   r   rÒ   r8   r+   r)   rŠ   rŠ   (  sÒ   € € € € € Ø€XÐ.Ð/Ñ/Ô/ð 15Ø!%Ø Ø26Ø$(ØðN
ð N
àðN
ð ˜‘˜oÑ-ðN
ð ˜$‘Jð	N
ð
 ðN
ð ˜jÑ(¨4Ñ/ðN
ð ˜T‘zðN
ð ðN
ð 
ðN
ð N
ð N
ñ 0Ô/ðN
ð N
ð N
r+   rŠ   )r   rE   rB   rŠ   )3Únumpyr$   Úhuggingface_hub.dataclassesr   Úaudio_utilsr   r   Úfeature_extraction_utilsr   Úmasking_utilsr   Úprocessing_utilsr	   Úutilsr
   r   r   r   r   r   r   Úutils.import_utilsr   r   Úxcodec2.configuration_xcodec2r   Ú"xcodec2.feature_extraction_xcodec2r   Úxcodec2.modeling_xcodec2r   r   r   r   r   r]   Útorch.nn.functionalÚnnÚ
functionalr˜   r‹   Ú
get_loggerr/   r²   r   r:   r>   r@   rB   rE   rŠ   Ú__all__r8   r+   r)   ú<module>rä      sR  ðð Ð Ð Ð Ø .Ð .Ð .Ð .Ð .Ð .à 9Ð 9Ð 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø 4Ð 4Ð 4Ð 4Ð 4Ð 4Ø 6Ð 6Ð 6Ð 6Ð 6Ð 6Ø &Ð &Ð &Ð &Ð &Ð &ðð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð DÐ CÐ CÐ CÐ CÐ CÐ CÐ CØ 9Ð 9Ð 9Ð 9Ð 9Ð 9Ø HÐ HÐ HÐ HÐ HÐ Hðð ð ð ð ð ð ð ð ð ð ð ð ð ð ÐÑÔð $Ø€L€L€LØ#Ð#Ð#Ð#Ð#Ð#Ð#Ð#Ð#àÐÑÔð ØÐÐÐð 
ˆÔ	˜HÑ	%Ô	%€ð €Ð/Ð0Ñ0Ô0Øð,cð ,cð ,cð ,cð ,c�]ñ ,cô ,cñ „ñ 1Ô0ð,cð^	ð 	ð 	ð 	ð 	�]ñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð0ñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð0ñ 	ô 	ð 	ð	ð 	ð 	ð 	ð 	Ð4ñ 	ô 	ð 	ð €ÐAÐBÑBÔBðm
ð m
ð m
ð m
ð m
�Lñ m
ô m
ñ CÔBðm
ð`P
ð P
ð P
ð P
ð P
Ð6ñ P
ô P
ð P
ðf eÐ
dÐ
d€€€r+   