|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
train_timesteps: 50 |
|
beta_start: 0.0001 |
|
beta_end: 0.05 |
|
|
|
residual_layers: 30 |
|
residual_channels: 64 |
|
dilation_cycle_length: 10 |
|
|
|
unconditional: False |
|
|
|
spec_n_mels: 80 |
|
spec_hop_length: 256 |
|
|
|
diffwave: !new:speechbrain.lobes.models.DiffWave.DiffWave |
|
input_channels: !ref <spec_n_mels> |
|
residual_layers: !ref <residual_layers> |
|
residual_channels: !ref <residual_channels> |
|
dilation_cycle_length: !ref <dilation_cycle_length> |
|
total_steps: !ref <train_timesteps> |
|
unconditional: !ref <unconditional> |
|
|
|
noise: !new:speechbrain.nnet.diffusion.GaussianNoise |
|
|
|
diffusion: !new:speechbrain.lobes.models.DiffWave.DiffWaveDiffusion |
|
model: !ref <diffwave> |
|
beta_start: !ref <beta_start> |
|
beta_end: !ref <beta_end> |
|
timesteps: !ref <train_timesteps> |
|
noise: !ref <noise> |
|
|
|
modules: |
|
diffwave: !ref <diffwave> |
|
diffusion: !ref <diffusion> |
|
|
|
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer |
|
loadables: |
|
diffwave: !ref <diffwave> |
|
|
