{
  "architectures": [
    "BSRoformerForMaskedEstimation"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_bs_roformer.BSRoformerConfig",
    "AutoModel": "modeling_bs_roformer.BSRoformerForMaskedEstimation"
  },
  "depth": 3,
  "freq_transformer_depth": 1,
  "freqs_per_bands": [
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    4,
    4,
    4,
    4,
    4,
    4,
    4,
    4,
    4,
    4,
    4,
    4,
    12,
    12,
    12,
    12,
    12,
    12,
    12,
    12,
    24,
    24,
    24,
    24,
    24,
    24,
    24,
    24,
    48,
    48,
    48,
    48,
    48,
    48,
    48,
    48,
    128,
    129
  ],
  "hidden_size": 256,
  "initializer_range": 0.02,
  "intermediate_size": 512,
  "mask_estimator_depth": 1,
  "model_type": "bs_roformer",
  "multi_stft_loss_hop_size": 147,
  "multi_stft_loss_weight": 0.0,
  "multi_stft_loss_window_sizes": [
    4096,
    2048,
    1024,
    512,
    256
  ],
  "num_attention_heads": 8,
  "num_input_channel": 2,
  "num_key_value_heads": 4,
  "num_stems": 4,
  "register_token_num": 4,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "stft_hop_length": 512,
  "stft_n_fft": 2048,
  "stft_win_length": 2048,
  "time_transformer_depth": 1,
  "torch_dtype": "float32",
  "transformers_version": "4.55.4"
}