| token_list: | |
| - <blank> | |
| - <unk> | |
| - a | |
| - o | |
| - i | |
| - '[' | |
| - '#' | |
| - u | |
| - ']' | |
| - e | |
| - k | |
| - n | |
| - t | |
| - r | |
| - s | |
| - N | |
| - m | |
| - _ | |
| - sh | |
| - d | |
| - g | |
| - ^ | |
| - $ | |
| - w | |
| - cl | |
| - h | |
| - y | |
| - b | |
| - j | |
| - ts | |
| - ch | |
| - z | |
| - p | |
| - f | |
| - ky | |
| - ry | |
| - gy | |
| - hy | |
| - ny | |
| - by | |
| - my | |
| - py | |
| - v | |
| - dy | |
| - '?' | |
| - ty | |
| - <sos/eos> | |
| odim: null | |
| model_conf: {} | |
| use_preprocessor: true | |
| token_type: phn | |
| bpemodel: null | |
| non_linguistic_symbols: null | |
| cleaner: jaconv | |
| g2p: pyopenjtalk_prosody | |
| feats_extract: linear_spectrogram | |
| feats_extract_conf: | |
| n_fft: 2048 | |
| hop_length: 512 | |
| win_length: null | |
| normalize: null | |
| normalize_conf: {} | |
| tts: vits | |
| tts_conf: | |
| generator_type: vits_generator | |
| generator_params: | |
| hidden_channels: 192 | |
| spks: -1 | |
| global_channels: -1 | |
| segment_size: 32 | |
| text_encoder_attention_heads: 2 | |
| text_encoder_ffn_expand: 4 | |
| text_encoder_blocks: 6 | |
| text_encoder_positionwise_layer_type: conv1d | |
| text_encoder_positionwise_conv_kernel_size: 3 | |
| text_encoder_positional_encoding_layer_type: rel_pos | |
| text_encoder_self_attention_layer_type: rel_selfattn | |
| text_encoder_activation_type: swish | |
| text_encoder_normalize_before: true | |
| text_encoder_dropout_rate: 0.1 | |
| text_encoder_positional_dropout_rate: 0.0 | |
| text_encoder_attention_dropout_rate: 0.1 | |
| use_macaron_style_in_text_encoder: true | |
| use_conformer_conv_in_text_encoder: false | |
| text_encoder_conformer_kernel_size: -1 | |
| decoder_kernel_size: 7 | |
| decoder_channels: 512 | |
| decoder_upsample_scales: | |
| - 8 | |
| - 8 | |
| - 2 | |
| - 2 | |
| - 2 | |
| decoder_upsample_kernel_sizes: | |
| - 16 | |
| - 16 | |
| - 4 | |
| - 4 | |
| - 4 | |
| decoder_resblock_kernel_sizes: | |
| - 3 | |
| - 7 | |
| - 11 | |
| decoder_resblock_dilations: | |
| - - 1 | |
| - 3 | |
| - 5 | |
| - - 1 | |
| - 3 | |
| - 5 | |
| - - 1 | |
| - 3 | |
| - 5 | |
| use_weight_norm_in_decoder: true | |
| posterior_encoder_kernel_size: 5 | |
| posterior_encoder_layers: 16 | |
| posterior_encoder_stacks: 1 | |
| posterior_encoder_base_dilation: 1 | |
| posterior_encoder_dropout_rate: 0.0 | |
| use_weight_norm_in_posterior_encoder: true | |
| flow_flows: 4 | |
| flow_kernel_size: 5 | |
| flow_base_dilation: 1 | |
| flow_layers: 4 | |
| flow_dropout_rate: 0.0 | |
| use_weight_norm_in_flow: true | |
| use_only_mean_in_flow: true | |
| stochastic_duration_predictor_kernel_size: 3 | |
| stochastic_duration_predictor_dropout_rate: 0.5 | |
| stochastic_duration_predictor_flows: 4 | |
| stochastic_duration_predictor_dds_conv_layers: 3 | |
| vocabs: 47 | |
| aux_channels: 1025 | |
| discriminator_type: hifigan_multi_scale_multi_period_discriminator | |
| discriminator_params: | |
| scales: 1 | |
| scale_downsample_pooling: AvgPool1d | |
| scale_downsample_pooling_params: | |
| kernel_size: 4 | |
| stride: 2 | |
| padding: 2 | |
| scale_discriminator_params: | |
| in_channels: 1 | |
| out_channels: 1 | |
| kernel_sizes: | |
| - 15 | |
| - 41 | |
| - 5 | |
| - 3 | |
| channels: 128 | |
| max_downsample_channels: 1024 | |
| max_groups: 16 | |
| bias: true | |
| downsample_scales: | |
| - 2 | |
| - 2 | |
| - 4 | |
| - 4 | |
| - 1 | |
| nonlinear_activation: LeakyReLU | |
| nonlinear_activation_params: | |
| negative_slope: 0.1 | |
| use_weight_norm: true | |
| use_spectral_norm: false | |
| follow_official_norm: false | |
| periods: | |
| - 2 | |
| - 3 | |
| - 5 | |
| - 7 | |
| - 11 | |
| period_discriminator_params: | |
| in_channels: 1 | |
| out_channels: 1 | |
| kernel_sizes: | |
| - 5 | |
| - 3 | |
| channels: 32 | |
| downsample_scales: | |
| - 3 | |
| - 3 | |
| - 3 | |
| - 3 | |
| - 1 | |
| max_downsample_channels: 1024 | |
| bias: true | |
| nonlinear_activation: LeakyReLU | |
| nonlinear_activation_params: | |
| negative_slope: 0.1 | |
| use_weight_norm: true | |
| use_spectral_norm: false | |
| generator_adv_loss_params: | |
| average_by_discriminators: false | |
| loss_type: mse | |
| discriminator_adv_loss_params: | |
| average_by_discriminators: false | |
| loss_type: mse | |
| feat_match_loss_params: | |
| average_by_discriminators: false | |
| average_by_layers: false | |
| include_final_outputs: true | |
| mel_loss_params: | |
| fs: 44100 | |
| n_fft: 2048 | |
| hop_length: 512 | |
| win_length: null | |
| window: hann | |
| n_mels: 80 | |
| fmin: 0 | |
| fmax: null | |
| log_base: null | |
| lambda_adv: 1.0 | |
| lambda_mel: 45.0 | |
| lambda_feat_match: 2.0 | |
| lambda_dur: 1.0 | |
| lambda_kl: 1.0 | |
| sampling_rate: 44100 | |
| cache_generator_outputs: true | |
| pitch_extract: null | |
| pitch_extract_conf: {} | |
| pitch_normalize: null | |
| pitch_normalize_conf: {} | |
| energy_extract: null | |
| energy_extract_conf: {} | |
| energy_normalize: null | |
| energy_normalize_conf: {} | |
| required: | |
| - output_dir | |
| - token_list | |
| version: '202308' | |
| distributed: false | |