ZjgSrSSKrSSKrSSKJr SSKJr SSKJ r SSK J r \ "SS 9\"S S \555r S /r g) zMimi model configurationN)strict)PreTrainedConfig)RopeParameters)auto_docstringz kyutai/mimi) checkpointc^\rSrSr%SrSrSr\\S'Sr \\S'Sr \\S 'S r \\S 'Sr \\S 'S r \\S -\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$'Sr\\S%'Sr\\S&'Sr \\S''S(r!\\S)'Sr"\\S*'S(r#\\S+'S(r$\\S,'S r%\S -\S-'S.r&\\S/'S0r'\\S1'S2r(\\S3'S4r)\\S5'S#r*\\S6'S#r+\\S7'S r,\-\.-S -\S8'S9r/\\S:'S;r0\\-\S<'S=r1\\S>'S#r2\\S?'Sr3\\S@'U4SAjr4SBr5\6SC\4SDj5r7\6SC\4SEj5r8\6SC\4SFj5r9\6SC\4SGj5r:SHr;U=r<$)I MimiConfiga audio_channels (`int`, *optional*, defaults to 1): Number of channels in the audio data. Either 1 for mono or 2 for stereo. num_filters (`int`, *optional*, defaults to 64): Number of convolution kernels of first `MimiConv1d` down sampling layer. num_residual_layers (`int`, *optional*, defaults to 1): Number of residual layers. upsampling_ratios (`Sequence[int]`, *optional*): Kernel size and stride ratios. The encoder uses downsampling ratios instead of upsampling ratios, hence it will use the ratios in the reverse order to the ones specified here that must match the decoder order. If not specified, will defaults to `[8, 6, 5, 4]` last_kernel_size (`int`, *optional*, defaults to 3): Kernel size for the last convolution layer. residual_kernel_size (`int`, *optional*, defaults to 3): Kernel size for the residual layers. dilation_growth_rate (`int`, *optional*, defaults to 2): How much to increase the dilation with each layer. use_causal_conv (`bool`, *optional*, defaults to `True`): Whether to use fully causal convolution. pad_mode (`str`, *optional*, defaults to `"constant"`): Padding mode for the convolutions. compress (`int`, *optional*, defaults to 2): Reduced dimensionality in residual branches. trim_right_ratio (`float`, *optional*, defaults to 1.0): Ratio for trimming at the right of the transposed convolution under the `use_causal_conv = True` setup. If equal to 1.0, it means that all the trimming is done at the right. num_quantizers (`int`, *optional*, defaults to 32): Number of quantizer channels, or codebooks, in the quantizer. use_conv_shortcut (`bool`, *optional*, defaults to `False`): Whether to use a convolutional layer as the 'skip' connection in the `MimiResnetBlock` block. If False, an identity function will be used, giving a generic residual connection. vector_quantization_hidden_dimension (`int`, *optional*, defaults to 256): Intermediate representation dimension in the residual vector quantization space. num_semantic_quantizers (`int`, *optional*, defaults to 1): Number of semantic quantizer channels, or codebooks, in the semantic quantizer. Must be lower than `num_quantizers`. upsample_groups (`int`, *optional*, defaults to 512): If `frame_rate!=encodec_frame_rate`, indicates the number of groups used in the upsampling operation to go from one rate to another. use_streaming (`bool`, *optional*, defaults to `False`): Whether to use streaming mode. If `True`, the model encode method will return the padding cache that can be used in a subsequent call to the encode method. Example: ```python >>> from transformers import MimiModel, MimiConfig >>> # Initializing a "kyutai/mimi" style configuration >>> configuration = MimiConfig() >>> # Initializing a model (with random weights) from the "kyutai/mimi" style configuration >>> model = MimiModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```mimii] sampling_rateaudio_channelsi hidden_size@ num_filtersnum_residual_layersNupsampling_ratios kernel_sizerlast_kernel_sizeresidual_kernel_sizedilation_growth_rateTuse_causal_convconstantpad_modecompressg?trim_right_ratioi codebook_size codebook_dim num_quantizersFuse_conv_shortcut$vector_quantization_hidden_dimensionnum_semantic_quantizersupsample_groupsnum_hidden_layersintermediate_sizenum_attention_headsnum_key_value_headshead_dimgelu hidden_acti@max_position_embeddingsg{Gz?initializer_rangegh㈵>norm_eps use_cache use_streamingrope_parameterssliding_windowgattention_dropoutg{Gz?layer_scale_initial_scaleattention_biastie_word_embeddingsc V>UR(a URO/SQUlURb URO URUlUR=(d URUR-UlUR SS5Ul[TU] "S0UD6 g)N)r) frame_rate) rr"rr.r,pop _frame_ratesuper __post_init__)selfkwargs __class__s |/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/mimi/configuration_mimi.pyrFMimiConfig.__post_init__}s;?;Q;Q!7!7Wc151B1B1ND--TXTdTd U)9)9T=U=U)U "::lD9 ''cURUR:a&[SURSURS35eg)zOPart of `@strict`-powered validation. Validates the architecture of the config.zVThe number of semantic quantizers should be lower than the total number of quantizers z, but is currently .N)r'r$ ValueErrorrGs rJvalidate_architecture MimiConfig.validate_architecturesg  ' '4+>+> >himi|i|h}~QRVRnRnQoopq  ?rLreturnc[R"UR5n[R"UR U- 5$N)npprodrmathceilr )rG hop_lengths rJencodec_frame_rateMimiConfig.encodec_frame_rates0WWT334 yy++j899rLcUR$rU)r$rPs rJ num_codebooksMimiConfig.num_codebookss"""rLcS/n[UR5Hn[UR5Hun[ UR [ 5(a[UR 5OSnURS/US--5 UR(dMdURS5 Mw URU5 M URS5 URS5 [R"U5$)Nrr) reversedrranger isinstancerlistlenextendr%appendrXrW)rGstridesratiojlen_kernel_sizess rJ frame_sizeMimiConfig.frame_sizes#d445E4334EOPTPiPikoEpEp3t'@'@#Avw s&6&:;<)))NN1% 5 NN5 !6 q qyy!!rLcfURb UR$URUR- $rU)rDr rlrPs rJrAMimiConfig.frame_rates1    '## #!!DOO33rL)rDr"r.r)=__name__ __module__ __qualname____firstlineno____doc__ model_typer int__annotations__rrrrrrdrrrrrboolrstrrrfloatr r"r$r%r&r'r(r*r+r,r-r.r0r1r2r3r4r5r6rdictr8r9r:r;r<rFrQpropertyr[r^rlrA__static_attributes__ __classcell__)rIs@rJr r s/5 nJM3NCKK  *.tCy4'.Kc !#! !#! OT HcHc!e!M3L#NC#t#03(#3#$S$OSs!s!    HcDjJ#'S'#u#HeItM448O^d*T18NC%(us{('+u+ ND $$(:C::#s##"C"".4E44rLr )rtrXnumpyrVhuggingface_hub.dataclassesrconfiguration_utilsrmodeling_rope_utilsrutilsrr __all__rBrLrJrsR .31#=)Y4!Y4*Y4x .rL