
    Z j                         S r SSKJr  SSKJr  SSKJr  \" SS9\ " S S	\5      5       5       r\" SS9\ " S
 S\5      5       5       rSS	/r	g)zParakeet model configuration.    )strict   )PreTrainedConfig)auto_docstringznvidia/parakeet-ctc-1.1b)
checkpointc                   |  ^  \ rS rSr% SrSrS/rSr\\	S'   Sr
\\	S'   S	r\\	S
'   Sr\\	S'   Sr\\	S'   Sr\\	S'   Sr\\	S'   Sr\\	S'   S	r\\	S'   Sr\\	S'   Sr\\	S'   Sr\\	S'   Sr\\	S'   Sr\\-  \	S'   Sr\\-  \	S '   Sr\\-  \	S!'   Sr\\-  \	S"'   Sr\\-  \	S#'   S$r\\	S%'   Sr\\	S&'   S'r \\	S('   U 4S) jr!S*r"U =r#$ )+ParakeetEncoderConfig   a}  
convolution_bias (`bool`, *optional*, defaults to `True`):
    Whether to use bias in convolutions of the conformer's convolution module.
conv_kernel_size (`int`, *optional*, defaults to 9):
    The kernel size of the convolution layers in the Conformer block.
subsampling_factor (`int`, *optional*, defaults to 8):
    The factor by which the input sequence is subsampled.
subsampling_conv_channels (`int`, *optional*, defaults to 256):
    The number of channels in the subsampling convolution layers.
num_mel_bins (`int`, *optional*, defaults to 80):
    Number of mel features.
subsampling_conv_kernel_size (`int`, *optional*, defaults to 3):
    The kernel size of the subsampling convolution layers.
subsampling_conv_stride (`int`, *optional*, defaults to 2):
    The stride of the subsampling convolution layers.
dropout_positions (`float`, *optional*, defaults to 0.0):
    The dropout ratio for the positions in the input sequence.
scale_input (`bool`, *optional*, defaults to `True`):
    Whether to scale the input embeddings.

Example:
    ```python
    >>> from transformers import ParakeetEncoderModel, ParakeetEncoderConfig

    >>> # Initializing a `ParakeetEncoder` configuration
    >>> configuration = ParakeetEncoderConfig()

    >>> # Initializing a model from the configuration
    >>> model = ParakeetEncoderModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```

This configuration class is based on the ParakeetEncoder architecture from NVIDIA NeMo. You can find more details
and pre-trained models at [nvidia/parakeet-ctc-1.1b](https://huggingface.co/nvidia/parakeet-ctc-1.1b).
parakeet_encoderpast_key_values   hidden_size   num_hidden_layers   num_attention_headsi   intermediate_sizesilu
hidden_actTattention_biasconvolution_bias	   conv_kernel_sizesubsampling_factor   subsampling_conv_channelsP   num_mel_binsr   subsampling_conv_kernel_size   subsampling_conv_strideg?dropoutg        dropout_positions	layerdropactivation_dropoutattention_dropouti  max_position_embeddingsscale_inputg{Gz?initializer_rangec                 H   > U R                   U l        [        TU ]  " S0 UD6  g N )r   num_key_value_headssuper__post_init__selfkwargs	__class__s     ڄ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/parakeet/configuration_parakeet.pyr/   #ParakeetEncoderConfig.__post_init__X   s!    #'#;#; ''    )r-   )$__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferencer   int__annotations__r   r   r   r   strr   boolr   r   r   r   r   r   r!   r"   floatr#   r$   r%   r&   r'   r(   r)   r/   __static_attributes____classcell__r3   s   @r4   r	   r	      s   $L $J#4"5Ks  !s!JND!d!c%(s(L#() #)#$S$GUS[%(us{( Ius{ &))%(us{(#'S'K#u#( (r6   r	   c                      ^  \ rS rSr% SrSrS\0rSr\	\
S'   Sr\\
S'   S	r\\
S
'   Sr\\-  S-  \
S'   Sr\	S-  \
S'   U 4S jrSrU =r$ )ParakeetCTCConfig]   a  
ctc_loss_reduction (`str`, *optional*, defaults to `"mean"`):
    Specifies the reduction to apply to the output of `torch.nn.CTCLoss`. Only relevant when training an
    instance of [`ParakeetForCTC`].
ctc_zero_infinity (`bool`, *optional*, defaults to `True`):
    Whether to zero infinite losses and the associated gradients of `torch.nn.CTCLoss`. Infinite losses mainly
    occur when the inputs are too short to be aligned to the targets. Only relevant when training an instance
    of [`ParakeetForCTC`].
encoder_config (`Union[dict, ParakeetEncoderConfig]`, *optional*):
    The config object or dictionary of the encoder.

Example:

```python
>>> from transformers import ParakeetForCTC, ParakeetCTCConfig
>>> # Initializing a Parakeet configuration
>>> configuration = ParakeetCTCConfig()
>>> # Initializing a model from the configuration
>>> model = ParakeetForCTC(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```
parakeet_ctcencoder_configi  
vocab_sizemeanctc_loss_reductionTctc_zero_infinityNr   pad_token_idc                   > [        U R                  [        5      (       a  [        S0 U R                  D6U l        OU R                  c  [        5       U l        U R                  R                  U l        [
        TU ]  " S0 UD6  g r+   )
isinstancerJ   dictr	   r)   r.   r/   r0   s     r4   r/   ParakeetCTCConfig.__post_init__   sg    d))400"7"N$:M:M"ND  ("7"9D!%!4!4!F!F''r6   )rJ   r)   )r7   r8   r9   r:   r;   r<   r	   sub_configsrK   r>   r?   rM   r@   rN   rA   rJ   rR   r   rO   r/   rC   rD   rE   s   @r4   rG   rG   ]   sg    0  J#%:;KJ$$"t"59ND++d29#L#*#( (r6   rG   N)
r;   huggingface_hub.dataclassesr   configuration_utilsr   utilsr   r	   rG   __all__r,   r6   r4   <module>rY      sy    $ . 3 # 56B(, B(  7B(J 56((( ((  7((V  7
8r6   