sample_config.json

{
  "dataset": {
    "acoustic_param": {
      "alpha": 0.410,
      "dtype": "float32",
      "f0_ceil": 800,
      "f0_floor": 71,
      "fft_length": 1024,
      "frame_period": 5,
      "order": 8,
      "pad_second": 0,
      "sampling_rate": 24000,
      "threshold_db": 25
    },
    "input_glob": "./input_feature/*.npy",
    "target_glob": "./target_feature/*.npy",
    "indexes_glob": "./aligned_indexes/*.npy",
    "in_features": [
      "mc"
    ],
    "out_features": [
      "mc"
    ],
    "train_crop_size": 512,
    "input_global_noise": 0.01,
    "input_local_noise": 0.01,
    "target_global_noise": 0.01,
    "target_local_noise": 0.01,
    "seed": 0,
    "num_test": 5
  },
  "model": {
    "in_channels": 9,
    "out_channels": 9,
    "generator_base_channels": 8,
    "generator_extensive_layers": 8,
    "discriminator_base_channels": 1,
    "discriminator_extensive_layers": 5,
    "weak_discriminator": true
  },
  "loss": {
    "adversarial": 0,
    "mse": 100
  },
  "project": {
    "name": "",
    "tags": []
  },
  "train": {
    "batchsize": 8,
    "gpu": 0,
    "log_iteration": 250,
    "snapshot_iteration": 10000,
    "stop_iteration": null,
    "optimizer": {
      "alpha": 0.0002,
      "beta1": 0.5,
      "beta2": 0.999,
      "name": "Adam"
    }
  }
}