U 5A·fHã@s:dZddlmZddlmZe e¡ZGdd„deƒZdS)z UnivNetModel model configurationé)ÚPretrainedConfig)Úloggingc sheZdZdZdZddddddgdddgd dd d gd dd d gd dd d ggdddd d df ‡fdd„ Z‡ZS)Ú UnivNetConfiga This is the configuration class to store the configuration of a [`UnivNetModel`]. It is used to instantiate a UnivNet vocoder 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 UnivNet [dg845/univnet-dev](https://huggingface.co/dg845/univnet-dev) architecture, which corresponds to the 'c32' architecture in [maum-ai/univnet](https://github.com/maum-ai/univnet/blob/master/config/default_c32.yaml). Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: model_in_channels (`int`, *optional*, defaults to 64): The number of input channels for the UnivNet residual network. This should correspond to `noise_sequence.shape[1]` and the value used in the [`UnivNetFeatureExtractor`] class. model_hidden_channels (`int`, *optional*, defaults to 32): The number of hidden channels of each residual block in the UnivNet residual network. num_mel_bins (`int`, *optional*, defaults to 100): The number of frequency bins in the conditioning log-mel spectrogram. This should correspond to the value used in the [`UnivNetFeatureExtractor`] class. resblock_kernel_sizes (`Tuple[int]` or `List[int]`, *optional*, defaults to `[3, 3, 3]`): A tuple of integers defining the kernel sizes of the 1D convolutional layers in the UnivNet residual network. The length of `resblock_kernel_sizes` defines the number of resnet blocks and should match that of `resblock_stride_sizes` and `resblock_dilation_sizes`. resblock_stride_sizes (`Tuple[int]` or `List[int]`, *optional*, defaults to `[8, 8, 4]`): A tuple of integers defining the stride sizes of the 1D convolutional layers in the UnivNet residual network. The length of `resblock_stride_sizes` should match that of `resblock_kernel_sizes` and `resblock_dilation_sizes`. resblock_dilation_sizes (`Tuple[Tuple[int]]` or `List[List[int]]`, *optional*, defaults to `[[1, 3, 9, 27], [1, 3, 9, 27], [1, 3, 9, 27]]`): A nested tuple of integers defining the dilation rates of the dilated 1D convolutional layers in the UnivNet residual network. The length of `resblock_dilation_sizes` should match that of `resblock_kernel_sizes` and `resblock_stride_sizes`. The length of each nested list in `resblock_dilation_sizes` defines the number of convolutional layers per resnet block. kernel_predictor_num_blocks (`int`, *optional*, defaults to 3): The number of residual blocks in the kernel predictor network, which calculates the kernel and bias for each location variable convolution layer in the UnivNet residual network. kernel_predictor_hidden_channels (`int`, *optional*, defaults to 64): The number of hidden channels for each residual block in the kernel predictor network. kernel_predictor_conv_size (`int`, *optional*, defaults to 3): The kernel size of each 1D convolutional layer in the kernel predictor network. kernel_predictor_dropout (`float`, *optional*, defaults to 0.0): The dropout probability for each residual block in the kernel predictor network. initializer_range (`float`, *optional*, defaults to 0.01): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. leaky_relu_slope (`float`, *optional*, defaults to 0.2): The angle of the negative slope used by the leaky ReLU activation. Example: ```python >>> from transformers import UnivNetModel, UnivNetConfig >>> # Initializing a Tortoise TTS style configuration >>> configuration = UnivNetConfig() >>> # Initializing a model (with random weights) from the Tortoise TTS style configuration >>> model = UnivNetModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` Zunivneté@é édréééé égg{®Gáz„?gš™™™™™É?c  s„t|ƒt|ƒkr t|ƒks*ntdƒ‚||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ tƒjf| ŽdS)Nz§`resblock_kernel_sizes`, `resblock_stride_sizes`, and `resblock_dilation_sizes` must all have the same length (which will be the number of resnet blocks in the model).)ÚlenÚ ValueErrorÚmodel_in_channelsÚmodel_hidden_channelsÚ num_mel_binsÚresblock_kernel_sizesÚresblock_stride_sizesÚresblock_dilation_sizesÚkernel_predictor_num_blocksÚ kernel_predictor_hidden_channelsÚkernel_predictor_conv_sizeÚkernel_predictor_dropoutÚinitializer_rangeÚleaky_relu_slopeÚsuperÚ__init__)ÚselfrrrrrrrrrrrrÚkwargs©Ú __class__©úU/tmp/pip-unpacked-wheel-zw5xktn0/transformers/models/univnet/configuration_univnet.pyrXs""ÿzUnivNetConfig.__init__)Ú__name__Ú __module__Ú __qualname__Ú__doc__Z model_typerÚ __classcell__r!r!rr"rs> órN) r&Zconfiguration_utilsrÚutilsrZ get_loggerr#Úloggerrr!r!r!r"Ús