| { | |
| "vocoder": { | |
| "vocoder": { | |
| "upsample_initial_channel": 1536, | |
| "resblock": "AMP1", | |
| "upsample_rates": [ | |
| 5, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2 | |
| ], | |
| "resblock_kernel_sizes": [ | |
| 3, | |
| 7, | |
| 11 | |
| ], | |
| "upsample_kernel_sizes": [ | |
| 11, | |
| 4, | |
| 4, | |
| 4, | |
| 4, | |
| 4 | |
| ], | |
| "resblock_dilation_sizes": [ | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ], | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ], | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ] | |
| ], | |
| "stereo": true, | |
| "use_tanh_at_final": false, | |
| "activation": "snakebeta", | |
| "use_bias_at_final": false | |
| }, | |
| "bwe": { | |
| "upsample_initial_channel": 512, | |
| "resblock": "AMP1", | |
| "upsample_rates": [ | |
| 6, | |
| 5, | |
| 2, | |
| 2, | |
| 2 | |
| ], | |
| "resblock_kernel_sizes": [ | |
| 3, | |
| 7, | |
| 11 | |
| ], | |
| "upsample_kernel_sizes": [ | |
| 12, | |
| 11, | |
| 4, | |
| 4, | |
| 4 | |
| ], | |
| "resblock_dilation_sizes": [ | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ], | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ], | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ] | |
| ], | |
| "stereo": true, | |
| "use_tanh_at_final": false, | |
| "activation": "snakebeta", | |
| "use_bias_at_final": false, | |
| "apply_final_activation": false, | |
| "input_sampling_rate": 16000, | |
| "output_sampling_rate": 48000, | |
| "hop_length": 80, | |
| "n_fft": 512, | |
| "win_size": 512, | |
| "num_mels": 64 | |
| } | |
| }, | |
| "_class_name": "LTX2Vocoder" | |
| } | |