vits-cantonese / model /config.json
xiaomaiiwn's picture
Upload config.json
edfd61e
{
"data": {
"add_blank": true,
"cleaned_text": true,
"filter_length": 1024,
"hop_length": 256,
"max_wav_value": 32768.0,
"mel_fmax": null,
"mel_fmin": 0.0,
"n_mel_channels": 80,
"n_speakers": 0,
"sampling_rate": 22050,
"text_cleaners": [
"chinese_dialect_cleaners"
],
"training_files": "/content/vits/filelists/list.txt.cleaned",
"validation_files": "/content/vits/filelists/lista.txt.cleaned",
"win_length": 1024
},
"model": {
"filter_channels": 768,
"hidden_channels": 192,
"inter_channels": 192,
"kernel_size": 3,
"n_heads": 2,
"n_layers": 6,
"n_layers_q": 3,
"p_dropout": 0.1,
"resblock": "1",
"resblock_dilation_sizes": [
[
1,
3,
5
],
[
1,
3,
5
],
[
1,
3,
5
]
],
"resblock_kernel_sizes": [
3,
7,
11
],
"upsample_initial_channel": 512,
"upsample_kernel_sizes": [
16,
16,
4,
4
],
"upsample_rates": [
8,
8,
2,
2
],
"use_spectral_norm": false
},
"speakers": [
"GD"
],
"symbols": [
"_",
",",
".",
"!",
"?",
"~",
"\u2026",
"\u2500",
"#",
"N",
"a",
"b",
"d",
"e",
"f",
"g",
"h",
"i",
"j",
"k",
"l",
"m",
"n",
"o",
"p",
"r",
"s",
"t",
"u",
"v",
"w",
"x",
"y",
"z",
"\u00e6",
"\u00e7",
"\u00f8",
"\u014b",
"\u0153",
"\u0235",
"\u0250",
"\u0251",
"\u0252",
"\u0253",
"\u0254",
"\u0255",
"\u0257",
"\u0258",
"\u0259",
"\u025a",
"\u025b",
"\u025c",
"\u0263",
"\u0264",
"\u0266",
"\u026a",
"\u026d",
"\u026f",
"\u0275",
"\u0277",
"\u0278",
"\u027b",
"\u027e",
"\u027f",
"\u0282",
"\u0285",
"\u028a",
"\u028b",
"\u028c",
"\u028f",
"\u0291",
"\u0294",
"\u02a6",
"\u02ae",
"\u02b0",
"\u02b7",
"\u02c0",
"\u02d0",
"\u02e5",
"\u02e6",
"\u02e7",
"\u02e8",
"\u02e9",
"\u0303",
"\u031a",
"\u0325",
"\u0329",
"\u1d00",
"\u1d07",
"\u2191",
"\u2193",
"\u2205",
"\u2c7c",
" "
],
"train": {
"batch_size": 12,
"betas": [
0.8,
0.99
],
"c_kl": 1.0,
"c_mel": 45,
"epochs": 2000,
"eps": 1e-09,
"eval_interval": 200,
"fp16_run": true,
"init_lr_ratio": 1,
"learning_rate": 0.0002,
"log_interval": 200,
"lr_decay": 0.999875,
"seed": 1234,
"segment_size": 8192,
"warmup_epochs": 0
}
}