vits-nyaru / configs /korean_base.json
rcell's picture
first commit
06a633a
{
"train": {
"log_interval": 200,
"eval_interval": 1000,
"seed": 1234,
"epochs": 10000,
"learning_rate": 2e-4,
"betas": [0.8, 0.99],
"eps": 1e-9,
"batch_size": 32,
"fp16_run": true,
"lr_decay": 0.999875,
"segment_size": 8192,
"init_lr_ratio": 1,
"warmup_epochs": 0,
"c_mel": 45,
"c_kl": 1.0
},
"data": {
"training_files":"filelists/train_filelist.txt.cleaned",
"validation_files":"filelists/val_filelist.txt.cleaned",
"text_cleaners":["korean_cleaners"],
"max_wav_value": 32768.0,
"sampling_rate": 22050,
"filter_length": 1024,
"hop_length": 256,
"win_length": 1024,
"n_mel_channels": 80,
"mel_fmin": 0.0,
"mel_fmax": null,
"add_blank": true,
"n_speakers": 6,
"cleaned_text": true
},
"model": {
"inter_channels": 192,
"hidden_channels": 192,
"filter_channels": 768,
"n_heads": 2,
"n_layers": 6,
"kernel_size": 3,
"p_dropout": 0.1,
"resblock": "1",
"resblock_kernel_sizes": [3,7,11],
"resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
"upsample_rates": [8,8,2,2],
"upsample_initial_channel": 512,
"upsample_kernel_sizes": [16,16,4,4],
"n_layers_q": 3,
"use_spectral_norm": false,
"gin_channels": 256
},
"speakers": ["\uc218\uc544", "\ubbf8\ubbf8\ub974", "\uc544\ub9b0", "\uc5f0\ud654", "\uc720\ud654", "\uc120\ubc30"],
"symbols": ["_", ",", ".", "!", "?", "\u2026", "~", "\u3131", "\u3134", "\u3137", "\u3139", "\u3141", "\u3142", "\u3145", "\u3147", "\u3148", "\u314a", "\u314b", "\u314c", "\u314d", "\u314e", "\u3132", "\u3138", "\u3143", "\u3146", "\u3149", "\u314f", "\u3153", "\u3157", "\u315c", "\u3161", "\u3163", "\u3150", "\u3154", " "]
}