config.json

{
  "output_dim": 384,
  "text_encoder_name": "sentence-transformers/all-MiniLM-L6-v2",
  "image_encoder_name": "google/siglip-base-patch16-512",
  "audio_encoder_name": "openai/whisper-tiny",
  "fusion_type": "transformer",
  "num_fusion_layers": 2,
  "enable_layer_outputs": true
}