ttsv/config/glow/base_blank.json

{
  "train": {
    "use_cuda": true,
    "log_interval": 20,
    "seed": 1234,
    "epochs": 10000,
    "learning_rate": 1e0,
    "betas": [0.9, 0.98],
    "eps": 1e-9,
    "warmup_steps": 4000,
    "scheduler": "noam",
    "batch_size": 16,
    "ddi": true,
    "fp16_run": true,
    "save_epoch": 1
  },
  "data": {
    "load_mel_from_disk": false,
    "training_files":"../data/training/train.txt", 
    "validation_files":"../data/training/valid.txt",
    "chars":"",
    "punc":"",
    "text_cleaners":["basic_indic_cleaners"],
    "max_wav_value": 32768.0,
    "sampling_rate": 22050,
    "filter_length": 1024,
    "hop_length": 256,
    "win_length": 1024,
    "n_mel_channels": 80,
    "mel_fmin": 80.0,
    "mel_fmax": 7600.0,
    "add_noise": true,
    "add_blank": true
  },
  "model": {
    "hidden_channels": 192,
    "filter_channels": 768,
    "filter_channels_dp": 256,
    "kernel_size": 3,
    "p_dropout": 0.1,
    "n_blocks_dec": 12,
    "n_layers_enc": 6,
    "n_heads": 2,
    "p_dropout_dec": 0.05,
    "dilation_rate": 1,
    "kernel_size_dec": 5,
    "n_block_layers": 4,
    "n_sqz": 2,
    "prenet": true,
    "mean_only": true,
    "hidden_channels_enc": 192,
    "hidden_channels_dec": 192,
    "window_size": 4
  }
}