File size: 2,248 Bytes
6742cf9 |
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 86 87 |
# pytorch_lightning==1.8.6
seed_everything: 4444
data:
class_path: vocos.dataset.VocosDataModule
init_args:
train_params:
filelist_path: ???
sampling_rate: 24000
num_samples: 16384
batch_size: 16
num_workers: 8
val_params:
filelist_path: ???
sampling_rate: 24000
num_samples: 48384
batch_size: 16
num_workers: 8
model:
class_path: vocos.experiment.VocosExp
init_args:
sample_rate: 24000
initial_learning_rate: 5e-4
mel_loss_coeff: 45
mrd_loss_coeff: 0.1
num_warmup_steps: 0 # Optimizers warmup steps
pretrain_mel_steps: 0 # 0 means GAN objective from the first iteration
# automatic evaluation
evaluate_utmos: true
evaluate_pesq: true
evaluate_periodicty: true
feature_extractor:
class_path: vocos.feature_extractors.MelSpectrogramFeatures
init_args:
sample_rate: 24000
n_fft: 1024
hop_length: 256
n_mels: 100
padding: center
backbone:
class_path: vocos.models.VocosResNetBackbone
init_args:
input_channels: 100
dim: 512
num_blocks: 3
head:
class_path: vocos.heads.ISTFTHead
init_args:
dim: 512
n_fft: 1024
hop_length: 256
padding: center
trainer:
logger:
class_path: pytorch_lightning.loggers.TensorBoardLogger
init_args:
save_dir: logs/
callbacks:
- class_path: pytorch_lightning.callbacks.LearningRateMonitor
- class_path: pytorch_lightning.callbacks.ModelSummary
init_args:
max_depth: 2
- class_path: pytorch_lightning.callbacks.ModelCheckpoint
init_args:
monitor: val_loss
filename: vocos_checkpoint_{epoch}_{step}_{val_loss:.4f}
save_top_k: 3
save_last: true
- class_path: vocos.helpers.GradNormCallback
# Lightning calculates max_steps across all optimizer steps (rather than number of batches)
# This equals to 1M steps per generator and 1M per discriminator
max_steps: 2000000
# You might want to limit val batches when evaluating all the metrics, as they are time-consuming
limit_val_batches: 100
accelerator: gpu
strategy: ddp
devices: [0]
log_every_n_steps: 100
|