+ œ°³j0(ãó|€Rt^RIt^RIt^RIHt^RIHt^RIHt]!RR7]!RR]444t R.t R#) zHubert model configurationN)Ústrict)ÚPreTrainedConfig)Úauto_docstringzfacebook/hubert-base-ls960)Ú checkpointcóøaa€]tRt^toRtRt^ tRt^ t^ t Rt Rt Rt Rt RtRtRtRtRtR tR tR tRtRtRtRtR t^€t^tR tR tRtR t ^ t!^t"Rt#^ t$^t%Rt&R t'R t(Rt)^t*^t+^t,V3Rlt-Rt.]/R4t0V3Rlt1Rt2Vt3V;t4#)Ú HubertConfigaÒ feat_proj_layer_norm (`bool`, *optional*, defaults to `True`): Whether to apply LayerNorm to the output of the feature encoder. feat_proj_dropout (`float`, *optional*, defaults to 0.0): The dropout probability for output of the feature encoder. final_dropout (`float`, *optional*, defaults to 0.1): The dropout probability for the final projection layer of [`Wav2Vec2ForCTC`]. feat_extract_norm (`str`, *optional*, defaults to `"group"`): The norm to be applied to 1D convolutional layers in feature encoder. One of `"group"` for group normalization of only the first 1D convolutional layer or `"layer"` for layer normalization of all 1D convolutional layers. feat_extract_activation (`str, `optional`, defaults to `"gelu"`): The non-linear activation function (function or string) in the 1D convolutional layers of the feature extractor. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. conv_dim (`tuple[int]`, *optional*, defaults to `(512, 512, 512, 512, 512, 512, 512)`): A tuple of integers defining the number of input and output channels of each 1D convolutional layer in the feature encoder. The length of *conv_dim* defines the number of 1D convolutional layers. conv_stride (`tuple[int]`, *optional*, defaults to `(5, 2, 2, 2, 2, 2, 2)`): A tuple of integers defining the stride of each 1D convolutional layer in the feature encoder. The length of *conv_stride* defines the number of convolutional layers and has to match the length of *conv_dim*. conv_kernel (`tuple[int]`, *optional*, defaults to `(10, 3, 3, 3, 3, 3, 3)`): A tuple of integers defining the kernel size of each 1D convolutional layer in the feature encoder. The length of *conv_kernel* defines the number of convolutional layers and has to match the length of *conv_dim*. conv_bias (`bool`, *optional*, defaults to `False`): Whether the 1D convolutional layers have a bias. num_conv_pos_embeddings (`int`, *optional*, defaults to 128): Number of convolutional positional embeddings. Defines the kernel size of 1D convolutional positional embeddings layer. num_conv_pos_embedding_groups (`int`, *optional*, defaults to 16): Number of groups of 1D convolutional positional embeddings layer. conv_pos_batch_norm (`bool`, *optional*, defaults to `False`): Whether to use batch norm instead of weight norm in conv_pos do_stable_layer_norm (`bool`, *optional*, defaults to `False`): Whether do apply *stable* layer norm architecture of the Transformer encoder. `do_stable_layer_norm is True` corresponds to applying layer norm before the attention layer, whereas `do_stable_layer_norm is False` corresponds to applying layer norm after the attention layer. apply_spec_augment (`bool`, *optional*, defaults to `True`): Whether to apply *SpecAugment* data augmentation to the outputs of the feature encoder. For reference see [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://huggingface.co/papers/1904.08779). mask_time_prob (`float`, *optional*, defaults to 0.05): Percentage (between 0 and 1) of all feature vectors along the time axis which will be masked. The masking procedure generates ''mask_time_prob*len(time_axis)/mask_time_length'' independent masks over the axis. If reasoning from the probability of each feature vector to be chosen as the start of the vector span to be masked, *mask_time_prob* should be `prob_vector_start*mask_time_length`. Note that overlap may decrease the actual percentage of masked vectors. This is only relevant if `apply_spec_augment is True`. mask_time_length (`int`, *optional*, defaults to 10): Length of vector span along the time axis. mask_time_min_masks (`int`, *optional*, defaults to 2),: The minimum number of masks of length `mask_feature_length` generated along the time axis, each time step, irrespectively of `mask_feature_prob`. Only relevant if ''mask_time_prob*len(time_axis)/mask_time_length < mask_time_min_masks'' mask_feature_prob (`float`, *optional*, defaults to 0.0): Percentage (between 0 and 1) of all feature vectors along the feature axis which will be masked. The masking procedure generates ''mask_feature_prob*len(feature_axis)/mask_time_length'' independent masks over the axis. If reasoning from the probability of each feature vector to be chosen as the start of the vector span to be masked, *mask_feature_prob* should be `prob_vector_start*mask_feature_length`. Note that overlap may decrease the actual percentage of masked vectors. This is only relevant if `apply_spec_augment is True`. mask_feature_length (`int`, *optional*, defaults to 10): Length of vector span along the feature axis. mask_feature_min_masks (`int`, *optional*, defaults to 0),: The minimum number of masks of length `mask_feature_length` generated along the feature axis, each time step, irrespectively of `mask_feature_prob`. Only relevant if ''mask_feature_prob*len(feature_axis)/mask_feature_length < mask_feature_min_masks'' ctc_loss_reduction (`str`, *optional*, defaults to `"sum"`): Specifies the reduction to apply to the output of `torch.nn.CTCLoss`. Only relevant when training an instance of [`HubertForCTC`]. ctc_zero_infinity (`bool`, *optional*, defaults to `False`): 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 [`HubertForCTC`]. use_weighted_layer_sum (`bool`, *optional*, defaults to `False`): Whether to use a weighted average of layer outputs with learned weights. Only relevant when using an instance of [`HubertForSequenceClassification`]. classifier_proj_size (`int`, *optional*, defaults to 256): Dimensionality of the projection before token mean-pooling for classification. Example: ```python >>> from transformers import HubertModel, HubertConfig >>> # Initializing a Hubert facebook/hubert-base-ls960 style configuration >>> configuration = HubertConfig() >>> # Initializing a model from the facebook/hubert-base-ls960 style configuration >>> model = HubertModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Úhubertii Úgelugš™™™™™¹?Tgg{®Gáz”?gñh㈵øä>ÚgroupFgš™™™™™©?Úsuméc ó\<€\VP4Vn\SV`!R/VBR#)N©)ÚlenÚconv_dimÚnum_feat_extract_layersÚsuperÚ __post_init__)ÚselfÚkwargsÚ __class__s&,€Úp/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/hubert/configuration_hubert.pyrÚHubertConfig.__post_init__¤s$ø€Ü'*¨4¯=©=Ó'9ˆÔ$Ü ‰ÒÑ' Ô'óc  óz€\VP4VP8wgI\VP4VP8wg%\VP4VP8wdO\ R\VP4 R\VP4 R\VP4 R24hR#)zOPart of `@strict`-powered validation. Validates the architecture of the config.zºConfiguration for convolutional layers is incorrect. It is required that `len(config.conv_dim)` == `len(config.conv_stride)` == `len(config.conv_kernel)`, but is `len(config.conv_dim) = z`, `len(config.conv_stride) = z`, `len(config.conv_kernel) = z`.N)rÚ conv_striderÚ conv_kernelrÚ ValueError©rs&rÚvalidate_architectureÚ"HubertConfig.validate_architecture¨s¦€ô×!Ñ!Ó " d×&BÑ&BÔ BÜD×$Ñ$Ó%¨×)EÑ)EÔEÜD—M‘MÓ" d×&BÑ&BÔBäð䘟 ™ Ó&Ð'Ð'EÄcÈ$×JZÑJZÓF[ÐE\ð]/Ü/2°4×3CÑ3CÓ/DÐ.EÀRðIóð ñCrcób€\P!\PVP^4#)é)Ú functoolsÚreduceÚoperatorÚmulrrs&rÚinputs_to_logits_ratioÚ#HubertConfig.inputs_to_logits_ratio¶s!€ä×Ò¤§ ¡ ¨d×.>Ñ.>ÀÓBÐBrcóT<€V^8„dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[S[,;R&S[S[,;R&S[S[,;R &S[;R &S[S[,;R &S[S[,;R &S[S[,;R &S[;R&S[;R&S[;R&S[;R&S[S[,S[S[R3,,;R&S[S[,S[S[R3,,;R&S[S[,S[S[R3,,;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[S[,;R&S[;R&S[;R&S[S[,;R&S[;R &S[;R!&S[;R"&S[;R#&S[;R$&S[;R%&S[R&,;R'&S[R&,;R(&S[S[S[,,R&,;R)&#)*éÚ vocab_sizeÚ hidden_sizeÚnum_hidden_layersÚnum_attention_headsÚintermediate_sizeÚ hidden_actÚhidden_dropoutÚactivation_dropoutÚattention_dropoutÚfeat_proj_layer_normÚfeat_proj_dropoutÚ final_dropoutÚ layerdropÚinitializer_rangeÚlayer_norm_epsÚfeat_extract_normÚfeat_extract_activation.rrrÚ conv_biasÚnum_conv_pos_embeddingsÚnum_conv_pos_embedding_groupsÚconv_pos_batch_normÚdo_stable_layer_normÚapply_spec_augmentÚmask_time_probÚmask_time_lengthÚmask_time_min_masksÚmask_feature_probÚmask_feature_lengthÚmask_feature_min_masksÚctc_loss_reductionÚctc_zero_infinityÚuse_weighted_layer_sumÚclassifier_proj_sizeNÚ pad_token_idÚ bos_token_idÚ eos_token_id)ÚintÚstrÚfloatÚboolÚlistÚtuple)ÚformatÚ __classdict__s"€rÚ __annotate__ÚHubertConfig.__annotate__s¶ø‡‚ñFÑñGñHÑñIñJÑñKñLÑ!ñMñNÑ!ñOñPÑñQñR™C•KÑ%ñSñT¡ Ñ)ñUñV™s•{Ñ(ñWñXÑ%ñYñZ™s•{Ñ(ñ[ñ\™3•;Ñ$ñ]ñ^‘s{Ñ ñ_ñ`Ñ#ñañbÑ ñcñdÑ$ñeñf!Ñ)ñgñh‘3i™%¡ S /Õ)ÑOñiñj‘c•™U¡3¨ 8_Õ,ÑDñkñl‘c•™U¡3¨ 8_Õ,ÑEñmñnÑñoñp!Ñ&ñqñr$'Ñ+ñsñtÑ%ñuñvÑ&ñwñxÑ#ñyñz™C•KÑ&ñ{ñ|Ññ}ñ~Ñ ññ@™s•{Ñ(ñAñBÑ!ñCñD Ñ#ñEñFÑ#ñGñHÑ#ñIñJ!Ñ(ñKñLÑ#ñMñN˜•*Ñ ñOñP˜•*Ñ ñQñR™™S •/ DÕ(Ñ,òSr)r)érYrYrYrYrYrY)ér*r*r*r*r*r*)é ér\r\r\r*r*)5Ú__name__Ú __module__Ú __qualname__Ú__firstlineno__Ú__doc__Ú model_typer+r,r-r.r/r0r1r2r3r4r5r6r7r8r9r:r;rrrr<r=r>r?r@rArBrCrDrErFrGrHrIrJrKrLrMrNrrÚpropertyr'Ú__annotate_func__Ú__static_attributes__Ú__classdictcell__Ú __classcell__)rrVs@@rrrsù‡€ñ\ ð|€Jà€JØ€KØÐØ!ÐØ!ÐØ€JØ"%€NØ&)ÐØ%(ÐØ!%ÐØ%(ÐØ!$€MØ €IØ#ÐØ €NØ$ÐØ#)ÐØ,O€HØ/D€KØ/E€KØ€IØ#&ÐØ)+Ð!Ø %ÐØ!&ÐØ#ÐØ"&€NØÐØ ÐØ%(ÐØ!ÐØ"#ÐØ#ÐØ#ÐØ#(ÐØ #ÐØ €LØ €LØ+,€Lõ(ò ðñCóðC÷}…rr) rar#r%Úhuggingface_hub.dataclassesrÚconfiguration_utilsrÚutilsrrÚ__all__rrrÚrlsTðñ!ãÛå.å3Ý#ñÐ7Ô8Øô]CÐ#ó]Cóó9ð]Cð@ Ð ‚r