| { |
| "type": "bigvgan", |
| "has_bwe_generator": true, |
| "vocoder": { |
| "upsample_initial_channel": 1536, |
| "resblock": "AMP1", |
| "upsample_rates": [5, 2, 2, 2, 2, 2], |
| "upsample_kernel_sizes": [11, 4, 4, 4, 4, 4], |
| "resblock_kernel_sizes": [3, 7, 11], |
| "resblock_dilation_sizes": [[1, 3, 5], [1, 3, 5], [1, 3, 5]], |
| "stereo": true, |
| "activation": "snakebeta", |
| "use_tanh_at_final": false, |
| "apply_final_activation": true, |
| "use_bias_at_final": false |
| }, |
| "bwe": { |
| "upsample_initial_channel": 512, |
| "resblock": "AMP1", |
| "upsample_rates": [6, 5, 2, 2, 2], |
| "upsample_kernel_sizes": [12, 11, 4, 4, 4], |
| "resblock_kernel_sizes": [3, 7, 11], |
| "resblock_dilation_sizes": [[1, 3, 5], [1, 3, 5], [1, 3, 5]], |
| "stereo": true, |
| "activation": "snakebeta", |
| "use_tanh_at_final": false, |
| "apply_final_activation": false, |
| "use_bias_at_final": false, |
| "input_sampling_rate": 16000, |
| "output_sampling_rate": 48000, |
| "hop_length": 80 |
| } |
| } |
|
|
