python/diarizen_sdk/model_meta.json

{
  "model_name": "diarizen-split",
  "task": "speaker_diarization_segmentation",
  "pipeline": "CNN_NPU + Backend_CPU",
  "components": {
    "cnn_npu": {
      "model": "cnn_features.axmodel",
      "input": {
        "name": "waveform_ln",
        "shape": [
          1,
          64000
        ],
        "dtype": "float32"
      },
      "output": {
        "name": "cnn_features",
        "shape": [
          1,
          199,
          211
        ],
        "dtype": "float32"
      },
      "hardware": "AX650 NPU U16"
    },
    "backend_cpu": {
      "model": "backend.onnx",
      "input": {
        "name": "cnn_features",
        "shape": [
          1,
          199,
          211
        ],
        "dtype": "float32"
      },
      "output": {
        "name": "log_probs",
        "shape": [
          1,
          199,
          11
        ],
        "dtype": "float32"
      },
      "hardware": "CPU FP32 (ONNX Runtime)"
    }
  },
  "preprocess": {
    "sample_rate": 16000,
    "duration_seconds": 4,
    "channels": 1,
    "layer_norm_eps": 1e-05,
    "description": "Resample to 16kHz mono, take 4s window, apply (x-mean)/sqrt(var+eps) LayerNorm"
  },
  "postprocess": {
    "description": "LogSoftmax output: frame-level log probabilities for 11 speaker activity classes"
  }
}