kiki-speaker-campplus-int8.onnx

Speaker embedding model CAM++ (trained on VoxCeleb) from the 3D-Speaker project
https://github.com/modelscope/3D-Speaker
Licensed under the Apache License, Version 2.0
https://www.apache.org/licenses/LICENSE-2.0

Modifications: exported to ONNX, dynamically quantized to int8, and the
AveragePool nodes set to count_include_pad=0 (same result, since their padding
is 0) so that ONNX Runtime Web computes the same values as other runtimes.
Used in Kiki Frost Web for in-browser speaker diarization. No other changes.