Upload reflow.yaml

configs/reflow.yaml

@@ -0,0 +1,52 @@
+data:
+  f0_extractor: 'rmvpe' # 'parselmouth', 'dio', 'harvest', 'crepe' or 'rmvpe'
+  f0_min: 65 # about C2
+  f0_max: 800 # about G5
+  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: 'contentvec768l12' # 'hubertsoft', 'hubertbase', 'hubertbase768', 'contentvec', 'contentvec768' or 'contentvec768l12' or 'cnhubertsoftfish'
+  cnhubertsoft_gate: 10
+  encoder_sample_rate: 16000
+  encoder_hop_size: 320
+  encoder_out_channels: 768 # 256 if using 'hubertsoft'
+  encoder_ckpt: pretrain/contentvec/checkpoint_best_legacy_500.pt
+  train_path: data/train # Create a folder named "audio" under this path and put the audio clip in it
+  valid_path: data/val # Create a folder named "audio" under this path and put the audio clip in it
+  extensions: # List of extension included in the data collection
+    - wav
+model:
+  type: 'RectifiedFlow'
+  win_length: 2048
+  n_layers: 6
+  n_chans: 512
+  t_start: 0.7
+  use_pitch_aug: true 
+  n_spk: 1 # max number of different speakers
+device: cuda # training device
+vocoder:
+  type: 'nsf-hifigan'
+  ckpt: 'pretrain/nsf_hifigan/model'
+infer:
+  infer_step: 20
+  method: 'euler' # 'euler', 'rk4'
+env:
+  expdir: exp/reflow-test
+  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: 96
+  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: 100
+  interval_val: 2000
+  interval_force_save: 10000
+  lr: 0.0002
+  decay_step: 50000
+  gamma: 0.5
+  weight_decay: 0
+  lambda_ddsp: 1
+  save_opt: false