2023-03-31 11:49:09 +02:00
|
|
|
{
|
|
|
|
|
"train": {
|
|
|
|
|
"log_interval": 200,
|
|
|
|
|
"seed": 1234,
|
|
|
|
|
"epochs": 20000,
|
|
|
|
|
"learning_rate": 1e-4,
|
|
|
|
|
"betas": [0.8, 0.99],
|
|
|
|
|
"eps": 1e-9,
|
|
|
|
|
"batch_size": 4,
|
2023-08-29 08:04:25 +02:00
|
|
|
"fp16_run": true,
|
2023-03-31 11:49:09 +02:00
|
|
|
"lr_decay": 0.999875,
|
2023-08-19 12:36:15 +02:00
|
|
|
"segment_size": 17280,
|
2023-03-31 11:49:09 +02:00
|
|
|
"init_lr_ratio": 1,
|
|
|
|
|
"warmup_epochs": 0,
|
|
|
|
|
"c_mel": 45,
|
|
|
|
|
"c_kl": 1.0
|
|
|
|
|
},
|
|
|
|
|
"data": {
|
|
|
|
|
"max_wav_value": 32768.0,
|
|
|
|
|
"sampling_rate": 48000,
|
|
|
|
|
"filter_length": 2048,
|
|
|
|
|
"hop_length": 480,
|
|
|
|
|
"win_length": 2048,
|
|
|
|
|
"n_mel_channels": 128,
|
|
|
|
|
"mel_fmin": 0.0,
|
|
|
|
|
"mel_fmax": null
|
|
|
|
|
},
|
|
|
|
|
"model": {
|
|
|
|
|
"inter_channels": 192,
|
|
|
|
|
"hidden_channels": 192,
|
|
|
|
|
"filter_channels": 768,
|
|
|
|
|
"n_heads": 2,
|
|
|
|
|
"n_layers": 6,
|
|
|
|
|
"kernel_size": 3,
|
|
|
|
|
"p_dropout": 0,
|
|
|
|
|
"resblock": "1",
|
|
|
|
|
"resblock_kernel_sizes": [3,7,11],
|
|
|
|
|
"resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
|
2023-08-19 12:36:15 +02:00
|
|
|
"upsample_rates": [12,10,2,2],
|
2023-03-31 11:49:09 +02:00
|
|
|
"upsample_initial_channel": 512,
|
2023-08-19 12:36:15 +02:00
|
|
|
"upsample_kernel_sizes": [24,20,4,4],
|
2023-03-31 11:49:09 +02:00
|
|
|
"use_spectral_norm": false,
|
|
|
|
|
"gin_channels": 256,
|
|
|
|
|
"spk_embed_dim": 109
|
|
|
|
|
}
|
|
|
|
|
}
|
