Open Jcwscience opened 2 years ago
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.
Hi, This link represents a script for converting the model to ONNX.
However, the performance was worse than the pure pytorch model.
Is there any one has any improvement for the model acceleration in TRT or ORT?
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.