preprocessor_config.json

{
  "do_normalize": false,
  "feature_extractor_type": "SpeechT5FeatureExtractor",
  "feature_size": 1,
  "fmax": 7600,
  "fmin": 80,
  "frame_signal_scale": 1.0,
  "hop_length": 16,
  "mel_floor": 1e-10,
  "n_fft": 1024,
  "n_freqs": 513,
  "num_mel_bins": 80,
  "padding_side": "right",
  "padding_value": 0.0,
  "processor_class": "SpeechT5Processor",
  "reduction_factor": 2,
  "return_attention_mask": true,
  "sample_size": 1024,
  "sample_stride": 256,
  "sampling_rate": 16000,
  "win_function": "hann_window",
  "win_length": 64
}