+ j ^RIHt^RIHt^RIHt]!RR7]!RR]444t]!RR7]!RR ]444tRR .tR #) )strict)PreTrainedConfig)auto_docstringz google/medasr) checkpointcaa]tRt^toRtRtR.tRt^t^t Rt Rt Rt Rt ^ tRt^t^t^tR tR tR tR tR tR tR tR tRtRtRtRtV3RltV3Rlt Rt!Vt"V;t##)LasrEncoderConfiga 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_valuesisiluFg?gi'g{Gz?gư>g{Gz?Nc J<VPVn\SV` !R/VBR#N)num_attention_headsnum_key_value_headssuper __post_init__selfkwargs __class__s&,l/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/lasr/configuration_lasr.pyrLasrEncoderConfig.__post_init__`s!#'#;#;  ''c<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;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[;R&S[;R&S[;R&S[S[,S[S[R3,,;R&S[S[,S[S[R3,,;R&S[;R&S[R,;R&#) hidden_sizenum_hidden_layersrintermediate_size hidden_actattention_biasconvolution_biasconv_kernel_sizesubsampling_conv_channels num_mel_binssubsampling_conv_kernel_sizesubsampling_conv_stridedropoutdropout_positions layerdropactivation_dropoutattention_dropoutmax_position_embeddingsinitializer_rangelayer_norm_eps.feed_forward_residual_weightsconv_residual_weightsbatch_norm_momentumNrope_parameters)intstrboolfloatlisttupledict)format __classdict__s"r __annotate__LasrEncoderConfig.__annotate__sXYZ[\ ]^!_`ab cd"efgh #(ijkl#&)mn!$opS[qrs{(sts{ uv )wxs{(yz!({|#}~ @$(;ucz1B#BOAB ;ucz)::GCD%EFD['Gr)r)g?g?)g@g?)$__name__ __module__ __qualname____firstlineno____doc__ model_typekeys_to_ignore_at_inferencerrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4r__annotate_func____static_attributes____classdictcell__ __classcell__rr=s@@rrrs$L J#4"5K !J N"%(L() #$G%( I&)%(#(# NEO!=G!%#'O(Krrcraa]tRt^etoRtRtR]/tRtRt Rt Rt ^t V3Rlt ]R 4tV3R ltR tVtV;t#) LasrCTCConfiga 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 meanTNc <\VP\4'd\R/VPBVnMVPf\4VnVPPVn\ SV`!R/VBR#r) isinstancerOr;rr/rrrs&,rrLasrCTCConfig.__post_init__sg d))4 0 0"3"Jd6I6I"JD   ("3"5D !%!4!4!F!F ''rc<VPP^,#)r)rOr()rs&rinputs_to_logits_ratio$LasrCTCConfig.inputs_to_logits_ratios""::A==rct<V^8dQh/S[;R&S[;R&S[;R&S[S[,R,;R&S[;R&#)r vocab_sizectc_loss_reductionctc_zero_infinityNrO pad_token_id)r5r6r7r;r)r<r=s"rr>LasrCTCConfig.__annotate__esU:;<$=>"?@++d29ABCr)rOr/)r@rArBrCrDrEr sub_configsrXrYrZrOr[rpropertyrUrGrHrIrJrKs@@rrMrMesX.J#%67KJ$"59NL(>>YrrMN) huggingface_hub.dataclassesrconfiguration_utilsrutilsrrrM__all__rrrrcss*/3#?+E((E(,E(P?++>$+>,+>\  0r