Masao Someki

Hi @neso613, Try re-install the latest `espnet_model_zoo`. If you still got the same error, please consider posting your issue on the `espnet_model_zoo` repository.

Thank you @PhenixCFLi, I think I get your issue right. Would you set `feats_dim` to your feature dimension? ```python from espnet_onnx.export import ASRModelExport m = ASRModelExport() m.set_export_config( max_seq_len=5000, feats_dim=85 )...

Sorry for the late replay @PhenixCFLi Now I get it! You are right, we need to skip that part if we have external feature. I think there is no way...

@PhenixCFLi Sorry for the late reply, I just created the PR to add export/inference without frontend module. After this PR has merged you can use your custom feature like this:...

Hi @Macsim2, sorry for the late reply. The converted model is on the CPU. I am not familiar with Triton server models, so I cannot help you with that part...

Thank you @csukuangfj, I think this might be caused by the version update...

@1nlplearner Thank you for reporting this issue. > when i delete postprocess code in [https://github.com/Masao-Someki/espnet_onnx/blob/master/espnet_onnx/tts/tts_model.py](https://github.com/espnet/espnet_onnx/issues/url) ，model can synthesis voice as pytorch inferencing It seems that the normalization process causes this...

I've completed all the reviews and added unit tests!