| { | |
| "train": { | |
| "log_interval": 1000, | |
| "eval_interval": 10000, | |
| "save_interval": 10000, | |
| "seed": 1234, | |
| "epochs": 1000, | |
| "optimizer": "adamw", | |
| "lr_decay_on": true, | |
| "learning_rate": 5e-5, | |
| "betas": [0.8, 0.99], | |
| "eps": 1e-9, | |
| "batch_size": 32, | |
| "fp16_run": false, | |
| "lr_decay": 0.999875, | |
| "segment_size": 35840, | |
| "init_lr_ratio": 1, | |
| "warmup_epochs": 0, | |
| "c_mel": 1, | |
| "aug": true, | |
| "lambda_commit": 0.02 | |
| }, | |
| "data": { | |
| "sampling_rate": 16000, | |
| "filter_length": 1280, | |
| "hop_length": 320, | |
| "win_length": 1280, | |
| "n_mel_channels": 80, | |
| "mel_fmin": 0, | |
| "mel_fmax": 8000 | |
| }, | |
| "model": { | |
| "inter_channels": 192, | |
| "hidden_channels": 192, | |
| "filter_channels": 768, | |
| "n_heads": 2, | |
| "n_layers": 8, | |
| "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": [5,4,2,2,2,2], | |
| "upsample_initial_channel": 1024, | |
| "upsample_kernel_sizes": [11,8,4,4,4,4], | |
| "hidden_size": 128 | |
| }, | |
| "diffusion" : { | |
| "dec_dim" : 64, | |
| "spk_dim" : 128, | |
| "beta_min" : 0.05, | |
| "beta_max" : 20.0 | |
| } | |
| } | |