v2/config.json

{
  "32000": {
    "model_type": "SynthesizerTrnMs768NSFsid",
    "version": "v2",
    "sample_rate": 32000,
    "f0": true,
    "spec_channels": 1025,
    "segment_size": 32,
    "inter_channels": 192,
    "hidden_channels": 192,
    "filter_channels": 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": [10, 8, 2, 2],
    "upsample_initial_channel": 512,
    "upsample_kernel_sizes": [20, 16, 4, 4],
    "spk_embed_dim": 109,
    "gin_channels": 256
  },
  "40000": {
    "model_type": "SynthesizerTrnMs768NSFsid",
    "version": "v2",
    "sample_rate": 40000,
    "f0": true,
    "spec_channels": 1025,
    "segment_size": 32,
    "inter_channels": 192,
    "hidden_channels": 192,
    "filter_channels": 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": [10, 10, 2, 2],
    "upsample_initial_channel": 512,
    "upsample_kernel_sizes": [20, 20, 4, 4],
    "spk_embed_dim": 109,
    "gin_channels": 256
  },
  "48000": {
    "model_type": "SynthesizerTrnMs768NSFsid",
    "version": "v2",
    "sample_rate": 48000,
    "f0": true,
    "spec_channels": 1025,
    "segment_size": 32,
    "inter_channels": 192,
    "hidden_channels": 192,
    "filter_channels": 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": [12, 10, 2, 2],
    "upsample_initial_channel": 512,
    "upsample_kernel_sizes": [24, 20, 4, 4],
    "spk_embed_dim": 109,
    "gin_channels": 256
  }
}