File size: 1,436 Bytes
5d4d3ed ae12110 5d4d3ed ae12110 c7221ed ae12110 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
vocab_size: 101
embedding_dim: 128
in_channels: 128
out_channels: 1
resblock_type: "1"
resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
resblock_kernel_sizes: [3, 7, 11]
upsample_kernel_sizes: [11, 8, 8, 4, 4]
upsample_initial_channel: 512
upsample_factors: [5, 4, 4, 2, 2]
inference_padding: 5
cond_channels: 0
conv_post_bias: True
var_pred_hidden_dim: 128
var_pred_kernel_size: 3
var_pred_dropout: 0.5
dur_prediction_weight: 1.0
generator: !new:speechbrain.lobes.models.HifiGAN.UnitHifiganGenerator
in_channels: !ref <in_channels>
out_channels: !ref <out_channels>
resblock_type: !ref <resblock_type>
resblock_dilation_sizes: !ref <resblock_dilation_sizes>
resblock_kernel_sizes: !ref <resblock_kernel_sizes>
upsample_kernel_sizes: !ref <upsample_kernel_sizes>
upsample_initial_channel: !ref <upsample_initial_channel>
upsample_factors: !ref <upsample_factors>
inference_padding: !ref <inference_padding>
cond_channels: !ref <cond_channels>
conv_post_bias: !ref <conv_post_bias>
vocab_size: !ref <vocab_size>
embedding_dim: !ref <embedding_dim>
duration_predictor: True
var_pred_hidden_dim: !ref <var_pred_hidden_dim>
var_pred_kernel_size: !ref <var_pred_kernel_size>
var_pred_dropout: !ref <var_pred_dropout>
pooling_type: none
modules:
generator: !ref <generator>
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
loadables:
generator: !ref <generator> |