config.json

{
  "model_type": "fastconformer_rnnt",
  "source_model": "nvidia/nemotron-speech-streaming-en-0.6b",
  "audio": {
    "sample_rate": 16000,
    "sample_format": "S16_LE",
    "bytes_per_second": 32000
  },
  "preprocessor": {
    "n_mels": 128,
    "n_fft": 512,
    "hop_length": 160,
    "win_length": 400,
    "window": "hann",
    "preemph": 0.97,
    "dither": 1e-05,
    "normalize": null,
    "pad_to": 0,
    "mel_norm": "slaney",
    "mel_layout": "band_major"
  },
  "encoder": {
    "model_file": "encoder_model.onnx",
    "layers": 24,
    "dim": 1024,
    "chunk_mel_frames": 16,
    "pre_encode_cache_frames": 9,
    "total_input_frames": 25,
    "cache_last_channel_shape": [
      1,
      24,
      70,
      1024
    ],
    "cache_last_time_shape": [
      1,
      24,
      1024,
      8
    ]
  },
  "decoder": {
    "model_file": "decoder_model.onnx",
    "prediction_layers": 2,
    "prediction_hidden": 640,
    "vocab_size": 1025,
    "blank_id": 1024,
    "max_symbols_per_frame": 10
  },
  "streaming": {
    "chunk_duration_ms": 160,
    "chunk_audio_samples": 2560
  }
}