{
  "numMelBins": 128,
  "sampleRate": 16000,
  "nFFT": 512,
  "hopLength": 160,
  "winLength": 400,
  "preEmphasis": 0.97,
  "encoderHidden": 1024,
  "encoderLayers": 24,
  "subsamplingFactor": 8,
  "decoderHidden": 640,
  "decoderLayers": 2,
  "vocabSize": 8192,
  "blankTokenId": 8192,
  "numDurationBins": 5,
  "durationBins": [
    0,
    1,
    2,
    3,
    4
  ]
}