htdemucs_ft_config.json

{
  "klass": "<class 'demucs.htdemucs.HTDemucs'>",
  "args": [],
  "kwargs": {
    "sources": [
      "drums",
      "bass",
      "other",
      "vocals"
    ],
    "audio_channels": 2,
    "samplerate": 44100,
    "channels": 48,
    "channels_time": null,
    "growth": 2,
    "nfft": 4096,
    "wiener_iters": 0,
    "end_iters": 0,
    "wiener_residual": false,
    "cac": true,
    "depth": 4,
    "rewrite": true,
    "multi_freqs": [],
    "multi_freqs_depth": 3,
    "freq_emb": 0.2,
    "emb_scale": 10,
    "emb_smooth": true,
    "kernel_size": 8,
    "stride": 4,
    "time_stride": 2,
    "context": 1,
    "context_enc": 0,
    "norm_starts": 4,
    "norm_groups": 4,
    "dconv_mode": 3,
    "dconv_depth": 2,
    "dconv_comp": 8,
    "dconv_init": 0.001,
    "bottom_channels": 512,
    "t_layers": 5,
    "t_hidden_scale": 4.0,
    "t_heads": 8,
    "t_dropout": 0.02,
    "t_layer_scale": true,
    "t_gelu": true,
    "t_emb": "sin",
    "t_max_positions": 10000,
    "t_max_period": 10000.0,
    "t_weight_pos_embed": 1.0,
    "t_cape_mean_normalize": true,
    "t_cape_augment": true,
    "t_cape_glob_loc_scale": [
      5000.0,
      1.0,
      1.4
    ],
    "t_sin_random_shift": 0,
    "t_norm_in": true,
    "t_norm_in_group": false,
    "t_group_norm": false,
    "t_norm_first": true,
    "t_norm_out": true,
    "t_weight_decay": 0.05,
    "t_lr": null,
    "t_sparse_self_attn": false,
    "t_sparse_cross_attn": false,
    "t_mask_type": "diag",
    "t_mask_random_seed": 42,
    "t_sparse_attn_window": 400,
    "t_global_window": 100,
    "t_sparsity": 0.95,
    "t_auto_sparsity": false,
    "t_cross_first": false,
    "rescale": 0.1
  }
}