voice/model.json

{
  "schema": "ai2apps.mlx-rvc-checkpoint/v1",
  "source": {
    "name": "native-mlx-training",
    "synthetic": false
  },
  "weights": {
    "name": "model.safetensors",
    "sha256": "f48790573f69181a6c484ef42b7c3c53e2e0c9aef20bb9fcdbe1b308f5fcb51b",
    "tensor_count": 353,
    "parameter_count": 28694338,
    "dtype": "float32"
  },
  "model": {
    "spec_channels": 1025,
    "segment_size": 36,
    "inter_channels": 192,
    "hidden_channels": 192,
    "filter_channels": 768,
    "heads": 2,
    "layers": 6,
    "kernel_size": 3,
    "dropout": 0.0,
    "resblock": "1",
    "resblock_kernel_sizes": [
      3,
      7,
      11
    ],
    "resblock_dilation_sizes": [
      [
        1,
        3,
        5
      ],
      [
        1,
        3,
        5
      ],
      [
        1,
        3,
        5
      ]
    ],
    "upsample_rates": [
      12,
      10,
      2,
      2
    ],
    "upsample_initial_channels": 512,
    "upsample_kernel_sizes": [
      24,
      20,
      4,
      4
    ],
    "speaker_count": 109,
    "speaker_embedding_channels": 256,
    "sample_rate": 48000,
    "feature_version": "v2",
    "uses_f0": true
  }
}