vits-nyaru / configs /japanese_base.json
rcell's picture
first commit
06a633a
{
"train": {
"log_interval": 200,
"eval_interval": 2000,
"seed": 1234,
"epochs": 10000,
"learning_rate": 2e-4,
"betas": [0.8, 0.99],
"eps": 1e-9,
"batch_size": 24,
"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/trainnn.txt.cleaned",
"validation_files":"filelists/val.txt.cleaned",
"text_cleaners":["japanese_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": 7,
"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": ["\u7dbe\u5730\u5be7\u3005", "\u56e0\u5e61\u3081\u3050\u308b", "\u671d\u6b66\u82b3\u4e43", "\u5e38\u9678\u8309\u5b50", "\u30e0\u30e9\u30b5\u30e1", "\u978d\u99ac\u5c0f\u6625", "\u5728\u539f\u4e03\u6d77"],
"symbols": ["_", ",", ".", "!", "?", "-", "A", "E", "I", "N", "O", "Q", "U", "a", "b", "d", "e", "f", "g", "h", "i", "j", "k", "m", "n", "o", "p", "r", "s", "t", "u", "v", "w", "y", "z", "\u0283", "\u02a7", "\u2193", "\u2191", " "]
}