| { |
| "_version_": "v2", |
| "data": { |
| "sampling_rate": 22050, |
| "filter_length": 1024, |
| "hop_length": 256, |
| "win_length": 1024, |
| "n_speakers": 0 |
| }, |
| "model": { |
| "zero_g": true, |
| "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 |
| ], |
| "gin_channels": 256 |
| } |
| } |