{
  "model_type": "audio-spatializer",
  "architecture": "CrossAttnSpatializer",
  "sample_rate": 24000,
  "n_fft": 1024,
  "hop_length": 512,
  "n_mels": 128,
  "audio_embed_dim": 512,
  "text_embed_dim": 512,
  "nhead": 8,
  "num_layers": 6,
  "output_channels": 4,
  "output_format": "foa",
  "training": {
    "framework": "pytorch-lightning",
    "final_epoch": 14,
    "final_step": 342,
    "checkpoint": "epoch=14-step=342.ckpt"
  },
  "spatial_parameters": {
    "direction": ["front", "front-left", "left", "back-left", "back", "back-right", "right", "front-right"],
    "elevation": ["down", "level", "up"],
    "distance": ["near", "mid", "far"],
    "room_size": ["small", "medium", "large"],
    "reverb": ["dry", "medium", "wet"]
  }
}