| { | |
| "train": { | |
| "log_interval": 20, | |
| "eval_interval": 1000, | |
| "seed": 1234, | |
| "epochs": 20000, | |
| "learning_rate": 2e-4, | |
| "betas": [0.8, 0.99], | |
| "eps": 1e-9, | |
| "batch_size": 32, | |
| "fp16_run": false, | |
| "lr_decay": 0.999875, | |
| "segment_size": 10240, | |
| "init_lr_ratio": 1, | |
| "warmup_epochs": 0, | |
| "c_mel": 45, | |
| "c_kl": 1.0, | |
| "use_sr": true, | |
| "max_speclen": 1024, | |
| "port": "8002", | |
| "fft_sizes": [384, 683, 171], | |
| "hop_sizes": [30, 60, 10], | |
| "win_lengths": [150, 300, 60], | |
| "window": "hann_window" | |
| }, | |
| "data": { | |
| "training_files":"./dataset/train.txt", | |
| "validation_files":"./dataset/test.txt", | |
| "text_cleaners":["english_cleaners2"], | |
| "max_wav_value": 32768.0, | |
| "sampling_rate": 16000, | |
| "filter_length": 1280, | |
| "hop_length": 320, | |
| "win_length": 1280, | |
| "n_mel_channels": 80, | |
| "mel_fmin": 0.0, | |
| "mel_fmax": null, | |
| "add_blank": true, | |
| "n_speakers": 0, | |
| "cleaned_text": true | |
| }, | |
| "model": { | |
| "ms_istft_vits": true, | |
| "mb_istft_vits": false, | |
| "istft_vits": false, | |
| "subbands": 4, | |
| "gen_istft_n_fft": 16, | |
| "gen_istft_hop_size": 4, | |
| "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": [5,4], | |
| "upsample_initial_channel": 512, | |
| "upsample_kernel_sizes": [16,16], | |
| "n_layers_q": 3, | |
| "use_spectral_norm": false, | |
| "gin_channels": 256, | |
| "use_sdp": false, | |
| "ssl_dim": 1024, | |
| "use_spk": false | |
| } | |
| } | |