^j{"jdZddlmZddlmZddlmZedeGdd eZd gZy ) zVITS model configuration)strict)PreTrainedConfig)auto_docstringzfacebook/mms-tts-eng) checkpointc eZdZUdZdZdZeed<dZeed<dZ eed<d Z eed <d Z eed <d Z e ed<dZeed<dZeezed<dZeed<dZeed<dZeed<dZeed<dZeezed<dZeezed<dZeezed<dZeed<dZeed <d Ze ed!<d"Zeed#<d$Zeed%<d&Zeed'<d(Ze ee!ed)fzed*<d+Z"e ee!ed)fzed,<d-Z#e ee!ed)fzed.<d/Z$e e!zed0<dZ%eed1<d Z&eed2<dZ'eed3<d4Z(eed5<d6Z)eed7<dZ*eed8<d9Z+eezed:<d Z,eed;<d<d Z/eed?<d@Z0eedA<dBZ1eedC<d"Z2eedD<dEZ3eezedF<dGZ4eezedH<dIZ5eedJ<dKZ6eedL<dMZ7eedN<dOZ8edOzedP<dQZ9yO)R VitsConfiga 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_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. 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. 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& vocab_size hidden_sizenum_hidden_layersnum_attention_heads window_sizeTuse_biasiffn_dimg? layerdroprffn_kernel_size flow_sizeispectrogram_binsrelu hidden_acthidden_dropoutattention_dropoutactivation_dropoutg{Gz?initializer_rangegh㈵>layer_norm_eps"use_stochastic_duration_prediction num_speakersrspeaker_embedding_sizeiupsample_initial_channel)r'rr.upsample_rates)r)rrupsample_kernel_sizes)r resblock_kernel_sizes)r#rr.r.resblock_dilation_sizesleaky_relu_slopedepth_separable_channelsdepth_separable_num_layers duration_predictor_flow_binsg@duration_predictor_tail_boundduration_predictor_kernel_sizeg?duration_predictor_dropoutduration_predictor_num_flows"duration_predictor_filter_channelsprior_encoder_num_flows prior_encoder_num_wavenet_layersr)$posterior_encoder_num_wavenet_layersr/wavenet_kernel_sizewavenet_dilation_rategwavenet_dropoutg? speaking_rategMbX? noise_scaleg?noise_scale_durationi> sampling_rateN pad_token_idct|jt|jk7r8tdt|jdt|jdy)zOPart of `@strict`-powered validation. Validates the architecture of the config.z'The length of `upsample_kernel_sizes` (z-) must match the length of `upsample_rates` ()N)lenr*r( ValueError)selfs v/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/vits/configuration_vits.pyvalidate_architecturez VitsConfig.validate_architecturese t)) *c$2E2E.F F9#d>X>X:Y9Z[%%()<)<%=$>aA  G):__name__ __module__ __qualname____doc__ model_typer int__annotations__rrrrrboolrrfloatrrrrstrrrrr r!r"r$r%r&r(listtupler*r-r0r1r2r3r5r6r7r8r9r;r<r=r>r?r@rArBrCrDrErFrMrNrLr r sIT lJJKs  KHdGS Ius{ OSIscJ"%NECK%%(us{(&) )#u# NE /3&3L#"#C#$'c'2>NDIc3h/>9G49uS#X6G9C49uS#X6C,MTE\M!e!$%c%&''(* #*+.!5.*+"C+.1 1() #).1&1#$S$,-$c-02(#2  !"3"#&OUS[&!$M53;$K"%%%M3#L#*#rNr N) rRhuggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__r[rNrLr`sJ.3#12M!M3M` .rN