The script to generate the egs/ files

[ntyoshi]

Hi, Thanks for this great work.
I'm trying to reproduce your paper results and ran script you gave us at README.md in order to generate the egs/ files of Valentini and DNS but json files weren't saved.
Please check my questions below.

1. I took a look at denoiser/audio.py and I wonder if json.dump(meta, sys.stdout, indent=4) at the bottom line worked in your environment.
   When I changed it to json.dump(meta, sys.argv[2], indent=4), the script looked work well in the case of valentini.
2. When I tried dns script after I cloned DNS-challenge (interspeech2020/master), the part of $testset/synthetic/reverb/noisy seemed to be weird because there is no directory. I guess it means $testset/synthetic/with_reverb/noisy but is it true? Or should I change the branch of the DNS-challenge repository?

Thank you!

[adefossez]

Hey @ntyoshi

For 1.: you need to redirect the output of the script: for instance python -m denoiser.audio NOISY_PATH > OUT_PATH/noisy.json, otherwise it will just print the list to stdout.

2. I'll fix the readme, the path is indeed with_reverb/noisy.

Let me know if you have other issues :)

[ntyoshi]

For 1., I think in README.md, the script python -m denoiser.audio $noisy_train egs/val/tr/noisy.json should be changed to python -m denoiser.audio $noisy_train > egs/val/tr/noisy.json (the other lines should be done as well).

[adefossez]

Correct :) Sorry I missed that.

[ntyoshi]

Thank you for confirmation!
It looks working well on my environment as well.

[adefossez]

I'll close the issue now, please reopen if you still encounter issues :)

[ntyoshi]

I asked here again: #61

@adefossez
Hi, let me ask about Valentini noisy.json here.
The script you gave us generate the noisy test set as egs/val/tt/noisy.json.
But at 5th line conf/dset/valentini.yaml, the default value of noisy_json is egs/valentini/ts/noisy.json.
Are they different?