base.yaml

# task
task_cls: null

#############
# dataset
#############
sort_by_len: true
raw_data_dir: null
binary_data_dir: null
binarizer_cls: null
binarization_args:
  shuffle: false
  num_workers: 0

audio_sample_rate: 44100
hop_size: 512
win_size: 2048
fft_size: 2048  # Extra window size is filled with 0 paddings to match this parameter
sampler_frame_count_grid: 6
ds_workers: 4
dataloader_prefetch_factor: 2

#########
# model
#########
hidden_size: 256
dropout: 0.1
use_pos_embed: true
enc_layers: 4
num_heads: 2
enc_ffn_kernel_size: 9
ffn_act: gelu
use_spk_id: false

###########
# optimization
###########
optimizer_args:
  optimizer_cls: torch.optim.AdamW
  lr: 0.0004
  beta1: 0.9
  beta2: 0.98
  weight_decay: 0
lr_scheduler_args:
  scheduler_cls: torch.optim.lr_scheduler.StepLR
  step_size: 50000
  gamma: 0.5
clip_grad_norm: 1

###########
# train and eval
###########
num_ckpt_keep: 5
accumulate_grad_batches: 1
log_interval: 100
num_sanity_val_steps: 1  # steps of validation at the beginning
val_check_interval: 2000
max_updates: 120000
max_batch_frames: 32000
max_batch_size: 100000
max_val_batch_frames: 60000
max_val_batch_size: 1
pe: parselmouth
pe_ckpt: 'checkpoints/rmvpe/model.pt'
hnsep: vr
hnsep_ckpt: 'checkpoints/vr/model.pt'
f0_min: 65
f0_max: 1100
num_valid_plots: 10

###########
# pytorch lightning
# Read https://lightning.ai/docs/pytorch/stable/common/trainer.html#trainer-class-api for possible values
###########
pl_trainer_accelerator: 'auto'
pl_trainer_devices: 'auto'
pl_trainer_precision: '16-mixed'
pl_trainer_num_nodes: 1
pl_trainer_strategy: 
  name: auto
  process_group_backend: nccl
  find_unused_parameters: false
nccl_p2p: true

###########
# finetune
###########
finetune_enabled: false
finetune_ckpt_path: null
finetune_ignored_params: []
finetune_strict_shapes: true

freezing_enabled: false
frozen_params: []