{
  "architectures": [
    "SmadForAudioClassification"
  ],
  "auto_map": {
    "AutoConfig": "configuration_smad.SmadConfig",
    "AutoModel": "modeling_smad.SmadForAudioClassification",
    "AutoModelForAudioClassification": "modeling_smad.SmadForAudioClassification"
  },
  "channels": [
    32,
    64,
    128,
    128
  ],
  "dropout": 0.2,
  "id2label": {
    "0": "speech_noise",
    "1": "speech_music",
    "2": "singing_music",
    "3": "none"
  },
  "label2id": {
    "speech_noise": 0,
    "speech_music": 1,
    "singing_music": 2,
    "none": 3
  },
  "model_type": "smad_crnn",
  "n_fft": 400,
  "num_labels": 4,
  "num_mels": 80,
  "rnn_hidden": 128,
  "rnn_type": "gru",
  "sample_rate": 16000,
  "segment_seconds": 4.0,
  "temperature": 0.709507268312107
}