{
  "architectures": [
    "AkikiVadForVoiceActivityDetection"
  ],
  "context_samples": 320,
  "convolutions": [
    {
      "dilation": 1,
      "padding": [
        1,
        1
      ],
      "stride": 1
    },
    {
      "dilation": 1,
      "padding": [
        1,
        1
      ],
      "stride": 2
    },
    {
      "dilation": 1,
      "padding": [
        1,
        1
      ],
      "stride": 2
    },
    {
      "dilation": 1,
      "padding": [
        1,
        1
      ],
      "stride": 1
    }
  ],
  "frontend": {
    "fft_size": 256,
    "padding_mode": "reflect",
    "right_padding": 64,
    "stft_hop": 128,
    "window_size": 256
  },
  "hidden_size": 128,
  "hop_samples": 256,
  "model_id": "akiki-vad-1.0",
  "model_type": "akiki_vad",
  "recurrent_type": "gru",
  "reduction": "single",
  "sample_rate": 16000,
  "source_model_id": "teacher-only623-v2-s1730",
  "threshold": 0.5,
  "torch_dtype": "float32"
}