config.json

{
    "dataset": {
        "extract_voice": true,
        "in_memory_percentage": 1,
        "noise_only_percent": 0.1,
        "num_condition_classes": 29,
        "path": "data/NSDTSEA/",
        "regain": 0.06,
        "sample_rate": 16000,
        "type": "nsdtsea"
    },
    "model": {
        "condition_encoding": "binary",
        "dilations": 9,
        "filters": {
            "lengths": {
                "res": 3,
                "final": [3, 3],
                "skip": 1
            },
            "depths": {
                "res": 128,
                "skip": 128,
                "final": [2048, 256]
            }
        },
        "num_stacks": 3,
        "target_field_length": 1601,
        "target_padding": 1
    },
    "optimizer": {
        "decay": 0.0,
        "epsilon": 1e-08,
        "lr": 0.001,
        "momentum": 0.9,
        "type": "adam"
    },
    "training": {
        "batch_size": 10,
        "early_stopping_patience": 16,
        "loss": {
            "out_1": {
                "l1": 1,
                "l2": 0,
                "weight": 1
            },
            "out_2": {
                "l1": 1,
                "l2": 0,
                "weight": 1
            }
        },
        "num_epochs": 250,
        "num_test_samples": 100,
        "num_train_samples": 1000,
        "path": "sessions/002",
        "verbosity": 1
    }
}