Accelerated inference with TensorRT

[Jcwscience]

I know on the FastSpeech GitHub project there is a documented way to convert the speech model through ONNX to run with TensorRT. Has anyone attempted this with Flowtron? I’m using an AGX Xavier and I figure there could be a performance increase.

[farzanehnakhaee70]

Hi,
This link represents a script for converting the model to ONNX.

However, the performance was worse than the pure pytorch model.

[farzanehnakhaee70]

Is there any one has any improvement for the model acceleration in TRT or ORT?