text_encoder/config.json

{
  "architectures": [
    "ClapModel"
  ],
  "audio_config": {
    "depths": [
      2,
      2,
      12,
      2
    ],
    "fusion_num_hidden_layers": 2,
    "hidden_size": 1024,
    "model_type": "clap_audio_model",
    "patch_embeds_hidden_size": 128,
    "projection_hidden_size": 768
  },
  "hidden_size": 768,
  "initializer_factor": 1.0,
  "logit_scale_init_value": 14.285714285714285,
  "model_type": "clap",
  "num_hidden_layers": 16,
  "projection_dim": 512,
  "projection_hidden_act": "relu",
  "text_config": {
    "classifier_dropout": null,
    "fusion_hidden_size": 768,
    "fusion_num_hidden_layers": 2,
    "initializer_range": 0.02,
    "model_type": "clap_text_model",
    "projection_hidden_size": 768
  },
  "torch_dtype": "float32",
  "transformers_version": "4.40.0"
}