File size: 2,694 Bytes
ae56147 da8a335 ae56147 da8a335 ae56147 da8a335 ae56147 |
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 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
# ################################
# Model: Tacotroon2 for TTS
# Authors: Jonas Freiknecht
# ################################
mask_padding: True
n_mel_channels: 80
n_symbols: 148
symbols_embedding_dim: 256
encoder_kernel_size: 5
encoder_n_convolutions: 3
encoder_embedding_dim: 256
attention_rnn_dim: 1024
attention_dim: 128
attention_location_n_filters: 32
attention_location_kernel_size: 31
n_frames_per_step: 1
decoder_rnn_dim: 512
prenet_dim: 128
max_decoder_steps: 1000
gate_threshold: 0.5
p_attention_dropout: 0.1
p_decoder_dropout: 0.1
postnet_embedding_dim: 256
postnet_kernel_size: 5
postnet_n_convolutions: 5
decoder_no_early_stopping: False
sample_rate: 22050
# Model
model: !new:speechbrain.lobes.models.Tacotron2.Tacotron2
mask_padding: !ref <mask_padding>
n_mel_channels: !ref <n_mel_channels>
# symbols
n_symbols: !ref <n_symbols>
symbols_embedding_dim: !ref <symbols_embedding_dim>
# encoder
encoder_kernel_size: !ref <encoder_kernel_size>
encoder_n_convolutions: !ref <encoder_n_convolutions>
encoder_embedding_dim: !ref <encoder_embedding_dim>
# attention
attention_rnn_dim: !ref <attention_rnn_dim>
attention_dim: !ref <attention_dim>
# attention location
attention_location_n_filters: !ref <attention_location_n_filters>
attention_location_kernel_size: !ref <attention_location_kernel_size>
# decoder
n_frames_per_step: !ref <n_frames_per_step>
decoder_rnn_dim: !ref <decoder_rnn_dim>
prenet_dim: !ref <prenet_dim>
max_decoder_steps: !ref <max_decoder_steps>
gate_threshold: !ref <gate_threshold>
p_attention_dropout: !ref <p_attention_dropout>
p_decoder_dropout: !ref <p_decoder_dropout>
# postnet
postnet_embedding_dim: !ref <postnet_embedding_dim>
postnet_kernel_size: !ref <postnet_kernel_size>
postnet_n_convolutions: !ref <postnet_n_convolutions>
decoder_no_early_stopping: !ref <decoder_no_early_stopping>
# Function that converts the text into a sequence of valid characters.
generator: !new:speechbrain.lobes.models.HifiGAN.HifiganGenerator
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>
modules:
generator: !ref <generator>
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
loadables:
generator: !ref <generator>
|