egs/vocoder/gan/bigvgan/exp_config.json

{
 "base_config": "egs/vocoder/gan/exp_config_base.json",
 "preprocess": {
 // acoustic features
 "extract_mel": true,
 "extract_audio": true,

 // Features used for model training
 "use_mel": true,
 "use_audio": true
 },
 "model": {
 "generator": "bigvgan",
 "bigvgan": {
 "resblock": "1",
 "activation": "snakebeta",
 "snake_logscale": true,
 "upsample_rates": [
 8,
 8,
 2,
 2,
 ],
 "upsample_kernel_sizes": [
 16,
 16,
 4,
 4
 ],
 "upsample_initial_channel": 512,
 "resblock_kernel_sizes": [
 3,
 7,
 11
 ],
 "resblock_dilation_sizes": [
 [
 1,
 3,
 5
 ],
 [
 1,
 3,
 5
 ],
 [
 1,
 3,
 5
 ]
 ]
 }
 },
 "train": {
 "criterions": [
 "feature",
 "discriminator",
 "generator",
 "mel",
 ]
 },
 "inference": {
 "batch_size": 1,
 }
}