Dinghao Zhou

Output label and its start time and end time in orign wav。

I am trying to do this feature now on transducer 。But I could not find any paper and article related。 Nguyễn Lê Huy 于 2020年12月15日周二 下午10:48写道： > @Mddct Oh, currently...

@usimarit It seems two steps: 1 calculate the mean_start_shift, mean_end_shift 2 apply shift on each start and end I will evaluate the accuracy later. But for other language or own...

It is almost difficult ，if the fine-tuning is performed without the participation of the original data

Any plan for this？

We can do BN or Ln by oberselves

1 https://pytorch.org/tutorials/recipes/recipes/tuning_guide.html ： 2 https://www.tensorflow.org/tfx/serving/saved_model_warmup Perhaps it would be better to provide a warmup interface when deploy server

May we can bump libtorch to v1.11 or higher Xingchen Song(宋星辰) ***@***.***> 于 2022年7月20日周三 22:48写道： > > 1. yes, and it is mostly caused by different versions of libtorch >...

Do we have plan to enhance post processing like puct restoring

> Do you have plan to implement Text to speech models? I found this： https://github.com/wenet-e2e/wetts