config.json

{
    "train": {
        "log_interval": 200,
        "eval_interval": 1000,
        "seed": 1234,
        "epochs": 1000,
        "learning_rate": 0.0002,
        "betas": [
            0.8,
            0.99
        ],
        "eps": 1e-09,
        "batch_size": 32,
        "fp16_run": false,
        "lr_decay": 0.999875,
        "segment_size": 8192,
        "init_lr_ratio": 1,
        "warmup_epochs": 0,
        "c_mel": 45,
        "c_kl": 1.0,
        "fft_sizes": [
            384,
            683,
            171
        ],
        "hop_sizes": [
            30,
            60,
            10
        ],
        "win_lengths": [
            150,
            300,
            60
        ],
        "window": "hann_window"
    },
    "data": {
        "use_mel_posterior_encoder": true,
        "training_files": "filelists/train.txt.cleaned",
        "validation_files": "filelists/val.txt.cleaned",
        "text_cleaners": [
            "mongolian_cleaners"
        ],
        "max_wav_value": 32768.0,
        "sampling_rate": 22050,
        "filter_length": 1024,
        "hop_length": 256,
        "win_length": 1024,
        "n_mel_channels": 80,
        "mel_fmin": 0.0,
        "mel_fmax": null,
        "add_blank": true,
        "n_speakers": 0,
        "cleaned_text": true
    },
    "model": {
        "model_dir": "/kaggle/working/MB-iSTFT-VITS2/logs/models/test",
        "monotonic_align": "sma_v1",
        "use_mel_posterior_encoder": true,
        "use_transformer_flows": true,
        "transformer_flow_type": "pre_conv2",
        "use_spk_conditioned_encoder": false,
        "use_noise_scaled_mas": true,
        "use_duration_discriminator": true,
        "duration_discriminator_type": "dur_disc_2",
        "ms_istft_vits": false,
        "mb_istft_vits": false,
        "istft_vits": true,
        "subbands": false,
        "gen_istft_n_fft": 16,
        "gen_istft_hop_size": 4,
        "inter_channels": 192,
        "hidden_channels": 96,
        "filter_channels": 768,
        "n_heads": 2,
        "n_layers": 3,
        "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
        ],
        "upsample_initial_channel": 256,
        "upsample_kernel_sizes": [
            16,
            16
        ],
        "n_layers_q": 3,
        "use_spectral_norm": false,
        "use_sdp": false
    }
}