[FastPitch1.1/PyTorch] How to improve performance on Long sentence when the FastPitch is trained on short sentence dataset?

[JohnHerry]

Related to FastPitch1.1/PyTorch

Describe the bug

My FastPitch model is trained with short sentence dataset, When we use it to synthesize long text sentence, the result audio will get smaller and smaller volume. Is there any suggestion to advance the FastPitch, Letting it synthesis long sentence without split when It was trained on short sentence dataset?

To Reproduce Steps to reproduce the behavior:

1. Install '...'
2. Set "..."
3. Launch '...'

Expected behavior A clear and concise description of what you expected to happen.

Environment Please provide at least:

• Container version (e.g. pytorch:19.05-py3):
• GPUs in the system: (e.g. 8x Tesla V100-SXM2-16GB):
• CUDA driver version (e.g. 418.67):