configs_template/diffusion_template.yaml

data:
  sampling_rate: 44100
  block_size: 512 # Equal to hop_length
  duration: 2 # Audio duration during training, must be less than the duration of the shortest audio clip
  encoder: 'vec768l12' # 'hubertsoft', 'vec256l9', 'vec768l12'
  cnhubertsoft_gate: 10
  encoder_sample_rate: 16000
  encoder_hop_size: 320
  encoder_out_channels: 768 # 256 if using 'hubertsoft'
  training_files: "filelists/train.txt"
  validation_files: "filelists/val.txt"
  extensions: # List of extension included in the data collection
    - wav
  unit_interpolate_mode: "nearest"
model:
  type: 'Diffusion'
  n_layers: 20
  n_chans: 512
  n_hidden: 256
  use_pitch_aug: true  
  n_spk: 1 # max number of different speakers
device: cuda
vocoder:
  type: 'nsf-hifigan'
  ckpt: 'pretrain/nsf_hifigan/model'
infer:
  speedup: 10
  method: 'dpm-solver' # 'pndm' or 'dpm-solver'
env:
  expdir: logs/44k/diffusion
  gpu_id: 0
train:
  num_workers: 2 # If your cpu and gpu are both very strong, set to 0 may be faster!
  amp_dtype: fp32 # fp32, fp16 or bf16 (fp16 or bf16 may be faster if it is supported by your gpu)
  batch_size: 48
  cache_all_data: true # Save Internal-Memory or Graphics-Memory if it is false, but may be slow
  cache_device: 'cpu' # Set to 'cuda' to cache the data into the Graphics-Memory, fastest speed for strong gpu
  cache_fp16: true
  epochs: 100000
  interval_log: 10
  interval_val: 2000
  interval_force_save: 10000
  lr: 0.0002
  decay_step: 100000
  gamma: 0.5
  weight_decay: 0
  save_opt: false
spk:
  'nyaru': 0