Parakeet/examples/clarinet/configs/clarinet_ljspeech.yaml

53 lines
732 B
YAML

data:
batch_size: 8
train_clip_seconds: 0.5
sample_rate: 22050
hop_length: 256
win_length: 1024
n_fft: 2048
n_mels: 80
valid_size: 16
conditioner:
upsampling_factors: [16, 16]
teacher:
n_loop: 10
n_layer: 3
filter_size: 2
residual_channels: 128
loss_type: "mog"
output_dim: 3
log_scale_min: -9
student:
n_loops: [10, 10, 10, 10, 10, 10]
n_layers: [1, 1, 1, 1, 1, 1]
filter_size: 3
residual_channels: 64
log_scale_min: -7
stft:
n_fft: 2048
win_length: 1024
hop_length: 256
loss:
lmd: 4
train:
learning_rate: 0.0005
anneal_rate: 0.5
anneal_interval: 200000
gradient_max_norm: 100.0
checkpoint_interval: 1000
eval_interval: 1000
max_iterations: 2000000