Reproducible script for training GSEGAN?

[ws-choi]

Hi @santi-pdp, thank you for open-sourcing this amazing project.

I am trying to reproduce training GSEGAN [1] from scratch.
However, I could not have found a reproducible script for it.
Could you let me know such a train script?

Since there are a lot of parameters and scripts, I am not sure which options I must select to reproduce it.
For example, I don't know which dataset I must select.

segan_pytorch/train_gsegan.py

Lines 137 to 159 in 6b831de

	dset = SEOnlineDataset(opts.data_root,
	distorteds=opts.distorted_roots,
	distorted_p=opts.distorted_p,
	noises_dir=opts.noises_dir,
	chunker=chunker,
	nsamples=opts.data_samples,
	transform=trans,
	utt2class=opts.utt2class,
	lab_transform=aco_transform,
	lab_folder=opts.lab_folder)
	"""
	else:
	# create Dataset(s) and Dataloader(s)
	assert opts.noisy_data_root is not None
	# a contaminated dataset is specified, use ChunkerSEDataset
	dset = RandomChunkSEDataset(opts.data_root,
	opts.noisy_data_root,
	opts.preemph,
	slice_size=opts.slice_size,
	transform=aco_transform)
	dloader = DataLoader(dset, batch_size=opts.batch_size,
	shuffle=True, num_workers=opts.num_workers,
	pin_memory=CUDA)

Could you let me know such a train script, similar to this one (for GSEGAN)?

python train.py --save_path ckpt_segan+ --batch_size 300 \
		--clean_trainset data/clean_trainset \
		--noisy_trainset data/noisy_trainset \
		--cache_dir data/cache

Best,
Woosung Choi
[1] Pascual, Santiago, Joan Serrà, and Antonio Bonafonte. "Towards generalized speech enhancement with generative adversarial networks." arXiv preprint arXiv:1904.03418 (2019). Interspeech

[ws-choi]

Also, can you let me know how I can reproduce the evaluation for GSEGAN?