{
    "model_type": "zipvoice_decoder4",
    "max_tokens": 384,
    "max_feat_len": 1024,
    "feat_dim": 100,
    "sampling_rate": 24000,
    "hop_length": 256,
    "num_step": 10,
    "t_shift": 0.5,
    "guidance_scale": 1.0,
    "speed": 1.0
}