Xuesong Yang

@paarthneekhara, thanks for your PR! please address this error: ``` File "/opt/conda/lib/python3.8/site-packages/nemo/collections/tts/losses/hifigan_losses.py", line 69, in forward loss += torch.mean(torch.abs(rl - gl)) RuntimeError: The size of tensor a (1882) must match...

Could you please try to fix the alerts as described here: https://lgtm.com/projects/g/NVIDIA/NeMo/rev/pr-f0d82e6d82662b60dc1c597bc403b4ac6dc1615a? Thanks.

@redoctopus @blisc this PR will be closed soon. Are we planning to merge to NeMo? I bet this is the final internship work.

thanks for PR. Please fix the alerts as detected by LGTM.com.

Haven't dived too deep for this PR, will do later today. A general question, is there any way we could add a unit test to validate if energy computation and...

@yzhang123 just in case you are aware of this new auto-stale and close feature. Please update otherwise it will be closed.

haven't seen the error before. @Lanzik could you pls share full stack of error log?

@catalwaysright Here shows how to convert to ONNX: https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/core/export.html?highlight=onnx

@borisfom Could you please share any advice here? Thanks.

It would be great if we have a unit test capturing this bug fix.