ZjQSSKJr SSKJr SSKJr \"SS9\"SS\555r\"SS9\"S S \555rSS /rg ) )strict)PreTrainedConfig)auto_docstringz google/medasr) checkpointc^\rSrSr%SrSrS/rSr\\ S'Sr \\ S'S r \\ S 'S r \\ S 'S r \\ S'Sr\\ S'Sr\\ S'Sr\\ S'Sr\\ S'Sr\\ S'Sr\\ S'Sr\\ S'Sr\\-\ S'Sr\\-\ S'Sr\\-\ S 'Sr\\-\ S!'Sr\\-\ S"'S#r\\ S$'S%r\\ S&'S'r\\ S('S)r \!\\"\S*4-\ S+'S,r#\!\\"\S*4-\ S-'S.r$\\ S/'S0r%\&S0-\ S1'U4S2jr'S3r(U=r)$)4LasrEncoderConfiga convolution_bias (`bool`, *optional*, defaults to `False`): Whether to use bias in convolutions of the conformer's convolution module. conv_kernel_size (`int`, *optional*, defaults to 32): The kernel size of the convolution layers in the Conformer block. subsampling_conv_channels (`int`, *optional*, defaults to 256): The number of channels in the subsampling convolution layers. subsampling_conv_kernel_size (`int`, *optional*, defaults to 5): 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. feed_forward_residual_weights (`tuple[float, float]`, *optional*, defaults to `[1.5, 0.5]`): The residual weights for the feed forward layers. conv_residual_weights (`tuple[float, float]`, *optional*, defaults to `[2.0, 1.0]`): The residual weights for the convolution layers. batch_norm_momentum (`float`, *optional*, defaults to 0.01): The momentum for the batch normalization layers Example: ```python >>> from transformers import LasrEncoderModel, LasrEncoderConfig >>> # Initializing a `LasrEncoder` configuration >>> configuration = LasrEncoderConfig() >>> # Initializing a model from the configuration >>> model = LasrEncoderModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` This configuration class is based on the LasrEncoder architecture from Google Health AI. You can find more details and pre-trained models at [google/medasr](https://huggingface.co/google/medasr). lasr_encoderpast_key_values hidden_sizenum_hidden_layersnum_attention_headsiintermediate_sizesilu hidden_actFattention_biasconvolution_bias conv_kernel_sizesubsampling_conv_channels num_mel_binssubsampling_conv_kernel_sizesubsampling_conv_strideg?dropoutgdropout_positions layerdropactivation_dropoutattention_dropouti'max_position_embeddingsg{Gz?initializer_rangegư>layer_norm_eps)g?g?.feed_forward_residual_weights)g@g?conv_residual_weightsg{Gz?batch_norm_momentumNrope_parametersc H>URUl[TU] "S0UD6 gN)rnum_key_value_headssuper __post_init__selfkwargs __class__s |/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/lasr/configuration_lasr.pyr3LasrEncoderConfig.__post_init__`s!#'#;#;  '')r1)*__name__ __module__ __qualname____firstlineno____doc__ model_typekeys_to_ignore_at_inferencerint__annotations__rrrrstrrboolrrrrrr!r"floatr#r$r%r&r'r(r)r*listtupler+r,r-dictr3__static_attributes__ __classcell__r7s@r8r r s_$L J#4"5Ks  !s!J ND "d"c%(s(L#() #)#$S$GUS[%(us{( Ius{ &) )%(us{(#(S(#u# NE EO!4;ucz1B#BO=G4;ucz)::G!%%#'OTD['((r:r c^\rSrSr%SrSrS\0rSr\ \ S'Sr \ \ S'S r \\ S 'S r\\-S -\ S'S r\ \ S 'U4Sjr\S5rSrU=r$) LasrCTCConfigea 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 [`LasrForCTC`]. 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 [`LasrForCTC`]. Example: ```python >>> from transformers import LasrForCTC, LasrCTCConfig >>> # Initializing a Lasr configuration >>> configuration = LasrCTCConfig() >>> # Initializing a model from the configuration >>> model = LasrForCTC(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` This configuration class is based on the Lasr CTC architecture from Google Health AI. You can find more details and pre-trained models at [google/medasr](https://huggingface.co/google/medasr). lasr_ctcencoder_configr vocab_sizemeanctc_loss_reductionTctc_zero_infinityNr pad_token_idc >[UR[5(a[S0URD6UlOURc[5UlURRUl[ TU]"S0UD6 gr/) isinstancerQrIr r(r2r3r4s r8r3LasrCTCConfig.__post_init__sg d))4 0 0"3"Jd6I6I"JD   ("3"5D !%!4!4!F!F ''r:c4URRS-$)Nr )rQr!)r5s r8inputs_to_logits_ratio$LasrCTCConfig.inputs_to_logits_ratios""::A==r:)rQr()r;r<r=r>r?r@r sub_configsrRrBrCrTrDrUrErQrIrrVr3propertyr[rJrKrLs@r8rNrNesr.J#%67KJ$$"t"59ND++d29L#(>>r:rNN) huggingface_hub.dataclassesrconfiguration_utilsrutilsrr rN__all__r0r:r8rcss*/3#?+E((E(,E(P?++>$+>,+>\  0r: