rvc/configs/44100.json

{
    "train": {
        "log_interval": 200,
        "seed": 1234,
        "learning_rate": 0.0001,
        "betas": [0.8, 0.99],
        "eps": 1e-09,
        "lr_decay": 0.999875,
        "segment_size": 15876,
        "c_mel": 45,
        "c_kl": 1.0
    },
    "data": {
        "max_wav_value": 32768.0,
        "sample_rate": 44100,
        "filter_length": 2048,
        "hop_length": 441,
        "win_length": 2048,
        "n_mel_channels": 160,
        "mel_fmin": 0.0,
        "mel_fmax": null
    },
    "model": {
        "inter_channels": 192,
        "hidden_channels": 192,
        "filter_channels": 768,
        "text_enc_hidden_dim": 768,
        "n_heads": 2,
        "n_layers": 6,
        "kernel_size": 3,
        "p_dropout": 0,
        "resblock": "1",
        "resblock_kernel_sizes": [3,7,11],
        "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
        "upsample_rates": [7,7,3,3],
        "upsample_initial_channel": 512,
        "upsample_kernel_sizes": [14,14,6,6],
        "use_spectral_norm": false,
        "gin_channels": 256,
        "spk_embed_dim": 109
    }
}