Model export

In this section, we describe various ways to export models.

• Export model.state_dict()
  • When to use it
  • How to export
  • How to use the exported model
  • Use the exported model to run decode.py
• Export model with torch.jit.trace()
  • When to use it
  • How to export
  • How to use the exported models
• Export model with torch.jit.script()
  • When to use it
  • How to export
  • How to use the exported model
• Export to ONNX
  • sherpa-onnx
  • Example
  • Download the pre-trained model
  • Export the model to ONNX
  • Decode sound files with exported ONNX models
• Export to ncnn
  • Export streaming Zipformer transducer models to ncnn
    • 1. Download the pre-trained model
    • 2. Install ncnn and pnnx
    • 3. Export the model via torch.jit.trace()
    • 4. Export torchscript model via pnnx
    • 5. Test the exported models in icefall
    • 6. Modify the exported encoder for sherpa-ncnn
  • Export ConvEmformer transducer models to ncnn
    • 1. Download the pre-trained model
    • 2. Install ncnn and pnnx
    • 3. Export the model via torch.jit.trace()
    • 4. Export torchscript model via pnnx
    • 5. Test the exported models in icefall
    • 6. Modify the exported encoder for sherpa-ncnn
    • 7. (Optional) int8 quantization with sherpa-ncnn
  • Export LSTM transducer models to ncnn
    • 1. Download the pre-trained model
    • 2. Install ncnn and pnnx
    • 3. Export the model via torch.jit.trace()
    • 4. Export torchscript model via pnnx
    • 5. Test the exported models in icefall
    • 6. Modify the exported encoder for sherpa-ncnn
    • 7. (Optional) int8 quantization with sherpa-ncnn