Seung-won Park

Try tensorflow version under 1.4.0. The `hps` API has changed around version 1.4~1.5, and this repository's code doesn't work after that.

@Adityagrao Here you go. This code is executable with `Tensorflow>=1.5.0`. https://github.com/seungwonpark/pointer-generator @abisee Would you mind listing this repository to ["About this code" section](https://github.com/abisee/pointer-generator/blob/master/README.md#about-this-code) of `README.md`, like: > Python 3, Tensorflow>=1.5.0...

비슷한 증상을 겪고 있습니다. JPype1-py3와 JDK를 모두 설치했습니다만, 아래에서 2번째 줄을 실행하면 아예 "Python의 작동이 중지되었습니다"가 뜨네요. ``` from konlpy.tag import Kkma kkma = Kkma() ``` 사용환경은 아래와 같습니다. Windows...

Hi, I used single 32GB V100 gpu. For multi-GPU training, I recommend you to have a look at JiaminRen’s implementation.

Hi, @lawlict Yes, our current SDR calculation process may cause SDR value to look strange since it evaluates only once.

@stegben That will be very helpful. Thanks a lot! Actually, I don't have spare time/resource to try this now. So whenever you get a new (perhaps better) result with this,...

Hi, @weedwind Thank you for letting me know! Yes, I was aware of that test list, but haven’t tried to measure the actual performance with that. Considering the followings, I...

TL; DR: (to the title of this issue) No, I haven’t tried yet but I don’t think I can.

Oh, looks like I had misunderstood your question. Sorry for that. 10.1dB is relatively high SDR for the mixed audios to have. The authors of VoiceFilter mentioned that the SDR...

> Did you ever compute the mean SDR for your test set? Not yet. > Why did you get a median SDR of 1.9 dB? Actually the value 1.9dB was...