T^(h<6`dZddlmZddlmZej eZGddeZdgZ y)zVITS model configuration)PretrainedConfig)loggingc,eZdZdZdZddddddd d d dd d d d d ddddddgdgdgdgdgdgdgd dd ddd dddddddddddd d!f,fd" ZxZS)# VitsConfiga! This is the configuration class to store the configuration of a [`VitsModel`]. It is used to instantiate a VITS model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the VITS [facebook/mms-tts-eng](https://huggingface.co/facebook/mms-tts-eng) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 38): Vocabulary size of the VITS model. Defines the number of different tokens that can be represented by the `inputs_ids` passed to the forward method of [`VitsModel`]. hidden_size (`int`, *optional*, defaults to 192): Dimensionality of the text encoder layers. num_hidden_layers (`int`, *optional*, defaults to 6): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 2): Number of attention heads for each attention layer in the Transformer encoder. window_size (`int`, *optional*, defaults to 4): Window size for the relative positional embeddings in the attention layers of the Transformer encoder. use_bias (`bool`, *optional*, defaults to `True`): Whether to use bias in the key, query, value projection layers in the Transformer encoder. ffn_dim (`int`, *optional*, defaults to 768): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. layerdrop (`float`, *optional*, defaults to 0.1): The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details. ffn_kernel_size (`int`, *optional*, defaults to 3): Kernel size of the 1D convolution layers used by the feed-forward network in the Transformer encoder. flow_size (`int`, *optional*, defaults to 192): Dimensionality of the flow layers. spectrogram_bins (`int`, *optional*, defaults to 513): Number of frequency bins in the target spectrogram. hidden_act (`str` or `function`, *optional*, defaults to `"relu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings and encoder. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. activation_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for activations inside the fully connected layer. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. use_stochastic_duration_prediction (`bool`, *optional*, defaults to `True`): Whether to use the stochastic duration prediction module or the regular duration predictor. num_speakers (`int`, *optional*, defaults to 1): Number of speakers if this is a multi-speaker model. speaker_embedding_size (`int`, *optional*, defaults to 0): Number of channels used by the speaker embeddings. Is zero for single-speaker models. upsample_initial_channel (`int`, *optional*, defaults to 512): The number of input channels into the HiFi-GAN upsampling network. upsample_rates (`Tuple[int]` or `List[int]`, *optional*, defaults to `[8, 8, 2, 2]`): A tuple of integers defining the stride of each 1D convolutional layer in the HiFi-GAN upsampling network. The length of `upsample_rates` defines the number of convolutional layers and has to match the length of `upsample_kernel_sizes`. upsample_kernel_sizes (`Tuple[int]` or `List[int]`, *optional*, defaults to `[16, 16, 4, 4]`): A tuple of integers defining the kernel size of each 1D convolutional layer in the HiFi-GAN upsampling network. The length of `upsample_kernel_sizes` defines the number of convolutional layers and has to match the length of `upsample_rates`. resblock_kernel_sizes (`Tuple[int]` or `List[int]`, *optional*, defaults to `[3, 7, 11]`): A tuple of integers defining the kernel sizes of the 1D convolutional layers in the HiFi-GAN multi-receptive field fusion (MRF) module. resblock_dilation_sizes (`Tuple[Tuple[int]]` or `List[List[int]]`, *optional*, defaults to `[[1, 3, 5], [1, 3, 5], [1, 3, 5]]`): A nested tuple of integers defining the dilation rates of the dilated 1D convolutional layers in the HiFi-GAN multi-receptive field fusion (MRF) module. leaky_relu_slope (`float`, *optional*, defaults to 0.1): The angle of the negative slope used by the leaky ReLU activation. depth_separable_channels (`int`, *optional*, defaults to 2): Number of channels to use in each depth-separable block. depth_separable_num_layers (`int`, *optional*, defaults to 3): Number of convolutional layers to use in each depth-separable block. duration_predictor_flow_bins (`int`, *optional*, defaults to 10): Number of channels to map using the unonstrained rational spline in the duration predictor model. duration_predictor_tail_bound (`float`, *optional*, defaults to 5.0): Value of the tail bin boundary when computing the unconstrained rational spline in the duration predictor model. duration_predictor_kernel_size (`int`, *optional*, defaults to 3): Kernel size of the 1D convolution layers used in the duration predictor model. duration_predictor_dropout (`float`, *optional*, defaults to 0.5): The dropout ratio for the duration predictor model. duration_predictor_num_flows (`int`, *optional*, defaults to 4): Number of flow stages used by the duration predictor model. duration_predictor_filter_channels (`int`, *optional*, defaults to 256): Number of channels for the convolution layers used in the duration predictor model. prior_encoder_num_flows (`int`, *optional*, defaults to 4): Number of flow stages used by the prior encoder flow model. prior_encoder_num_wavenet_layers (`int`, *optional*, defaults to 4): Number of WaveNet layers used by the prior encoder flow model. posterior_encoder_num_wavenet_layers (`int`, *optional*, defaults to 16): Number of WaveNet layers used by the posterior encoder model. wavenet_kernel_size (`int`, *optional*, defaults to 5): Kernel size of the 1D convolution layers used in the WaveNet model. wavenet_dilation_rate (`int`, *optional*, defaults to 1): Dilation rates of the dilated 1D convolutional layers used in the WaveNet model. wavenet_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the WaveNet layers. speaking_rate (`float`, *optional*, defaults to 1.0): Speaking rate. Larger values give faster synthesised speech. noise_scale (`float`, *optional*, defaults to 0.667): How random the speech prediction is. Larger values create more variation in the predicted speech. noise_scale_duration (`float`, *optional*, defaults to 0.8): How random the duration prediction is. Larger values create more variation in the predicted durations. sampling_rate (`int`, *optional*, defaults to 16000): The sampling rate at which the output audio waveform is digitalized expressed in hertz (Hz). Example: ```python >>> from transformers import VitsModel, VitsConfig >>> # Initializing a "facebook/mms-tts-eng" style configuration >>> configuration = VitsConfig() >>> # Initializing a model (with random weights) from the "facebook/mms-tts-eng" style configuration >>> model = VitsModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```vits&Tig?rirelug{Gz?gh㈵>i)rr r )rr r )r )rr g@g?rrgg?gMbX?g?i>c- ||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_||_||_||_||_||_||_||_||_||_||_||_||_||_||_||_| |_|!|_ |"|_!|#|_"|$|_#|%|_$|&|_%|'|_&|(|_'|)|_(|*|_)|+|_*|,|_+tY|tY|k7r$t[dtY|dtY|dt].|di|-y)Nz'The length of `upsample_kernel_sizes` (z-) must match the length of `upsample_rates` ())0 vocab_size hidden_sizenum_hidden_layersnum_attention_heads window_sizeuse_biasffn_dim layerdropffn_kernel_size flow_sizespectrogram_bins hidden_acthidden_dropoutattention_dropoutactivation_dropoutinitializer_rangelayer_norm_eps"use_stochastic_duration_prediction num_speakersspeaker_embedding_sizeupsample_initial_channelupsample_ratesupsample_kernel_sizesresblock_kernel_sizesresblock_dilation_sizesleaky_relu_slopedepth_separable_channelsdepth_separable_num_layersduration_predictor_flow_binsduration_predictor_tail_boundduration_predictor_kernel_sizeduration_predictor_dropoutduration_predictor_num_flows"duration_predictor_filter_channelsprior_encoder_num_flows prior_encoder_num_wavenet_layers$posterior_encoder_num_wavenet_layerswavenet_kernel_sizewavenet_dilation_ratewavenet_dropout speaking_rate noise_scalenoise_scale_duration sampling_ratelen ValueErrorsuper__init__)/selfrrrrrrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCrDrEkwargs __class__s/ i/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/vits/configuration_vits.pyrIzVitsConfig.__init__s`%&!2#6 &   "." 0$,!2"4!2,2T/(&<#(@%,%:"%:"'>$ 0(@%*D',H)-J*.L+*D',H)2T/'>$0P-4X1#6 %:".*&$8!* $ %^)< <9#>S:T9UV%%(%8$9<  "6")__name__ __module__ __qualname____doc__ model_typerI __classcell__)rLs@rMrrsz xJ+/ !$#,(!*Iy A!"#$%'&)'(#&%&+. !)*-/ [c#c#rNrN) rRconfiguration_utilsrutilsr get_loggerrOloggerr__all__rrNrMrZs=3   H %b#!b#J .rN