Model Conversion
ONNX Export
python3 export_cnn_onnx.py
Exports the WavLM CNN feature extractor (7 conv layers).
- Input: LayerNorm-preprocessed waveform (1, 64000) float32
- Output: CNN features (1, 199, 211) float32
- Opset: 16
- Prerequisites: PyTorch, torchaudio, onnx, onnxruntime, toml
Pulsar2 Compilation
./compile_pulsar2.sh
Uses pulsar2:6.0-lite Docker image.
- Target: AX650, NPU3
- Quantization: all layers U16, MinMax calibration
- Calibration: 10 overlapping 4s windows from example audio
- Output: cnn_features.axmodel (~1.5MB)