| { | |
| "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": "melgan", | |
| "melgan": { | |
| "ratios": [8, 8, 2, 2], | |
| "ngf": 32, | |
| "n_residual_layers": 3, | |
| "num_D": 3, | |
| "ndf": 16, | |
| "n_layers": 4, | |
| "downsampling_factor": 4 | |
| }, | |
| }, | |
| "train": { | |
| "criterions": [ | |
| "feature", | |
| "discriminator", | |
| "generator", | |
| ] | |
| }, | |
| "inference": { | |
| "batch_size": 1, | |
| } | |
| } | |