egs/vocoder/gan/tfr_enhanced_hifigan/exp_config.json

{
  "base_config": "egs/vocoder/gan/exp_config_base.json",
  "model_type": "GANVocoder",
  "dataset": [
    "ljspeech",
    "vctk",
    "libritts",
  ],
  "dataset_path": {
    // TODO: Fill in your dataset path
    "ljspeech": "[dataset path]",
    "vctk": "[dataset path]",
    "libritts": "[dataset path]",
  },
  // TODO: Fill in the output log path. The default value is "Amphion/ckpts/vocoder"
  "log_dir": "ckpts/vocoder",
  "preprocess": {
    // TODO: Fill in the output data path. The default value is "Amphion/data"
    "processed_dir": "data",
    // acoustic features
    "extract_mel": true,
    "extract_audio": true,
    "extract_pitch": false,
    "extract_uv": false,
    "extract_amplitude_phase": false,
    "pitch_extractor": "parselmouth",
    // Features used for model training
    "use_mel": true,
    "use_frame_pitch": false,
    "use_uv": false,
    "use_audio": true,
    "n_mel": 100,
    "sample_rate": 24000
  },
  "model": {
    "generator": "hifigan",
    "discriminators": [
      "msd",
      "mpd",
      "mssbcqtd",
      "msstftd",
    ],
    "hifigan": {
      "resblock": "1",
      "upsample_rates": [
        8,
        4,
        2,
        2,
        2
      ],
      "upsample_kernel_sizes": [
        16,
        8,
        4,
        4,
        4
      ],
      "upsample_initial_channel": 768,
      "resblock_kernel_sizes": [
        3,
        5,
        7
      ],
      "resblock_dilation_sizes": [
        [
          1,
          3,
          5
        ],
        [
          1,
          3,
          5
        ],
        [
          1,
          3,
          5
        ]
      ]
    },
    "mpd": {
      "mpd_reshapes": [
        2,
        3,
        5,
        7,
        11,
        17,
        23,
        37
      ],
      "use_spectral_norm": false,
      "discriminator_channel_multi": 1
    }
  },
  "train": {
    "batch_size": 32,
    "adamw": {
      "lr": 2.0e-4,
      "adam_b1": 0.8,
      "adam_b2": 0.99
    },
    "exponential_lr": {
      "lr_decay": 0.999
    },
    "criterions": [
      "feature",
      "discriminator",
      "generator",
      "mel",
    ]
  },
  "inference": {
    "batch_size": 1,
  }
}