Soohwan Kim comments

Results 80 comments of


                                            Soohwan Kim

Testing performance of the re-produced model

I'm afraid I've heard from one of the contributors, so I don't have any more information.

Any pre-trained model provided?

Unfortunately, we don't provide pre-train model.

Any pre-trained model provided?

Check https://github.com/SoftwareImpacts/SIMPAC-2020-63

Any pre-trained model provided?

See https://github.com/sooftware/kospeech/issues/154

초심자 분들을 위한 DeepSpeech2 Pre-trained 모델 공유 드립니다.

너무 좋은 컨트리뷰션 감사합니다!!

초심자 분들을 위한 DeepSpeech2 Pre-trained 모델 공유 드립니다.

리드미쪽에 적절하게 PR 날려주셔도 감사하겠습니다 :)

Value Error Occured in training dataset with Jasper Model

Hi @Daeyeop-Kim. This repository is archived. Further development is underway [here](https://github.com/openspeech-team/openspeech).

Why are the error rate accumulated?

Hi @OleguerCanal! Thank you for your good opinion! I recycled the code that I made before, so I made it like this. @upskyy As @OleguerCanal said, why don't we add...

Why are the error rate accumulated?

I think `batch` would be good as the default value.

Expected period of time hanging(or pre-processing) in the beginning of the training

Five hours is a little strange. If there's no progress bar, it seems to be blocked somewhere.