From 23d55358906254ada24ac84674b07881921aa38c Mon Sep 17 00:00:00 2001 From: djmoffat Date: Fri, 24 Sep 2021 11:16:32 +0100 Subject: [PATCH] Correct dataset mistake in README --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 73b2840..6b0c300 100644 --- a/README.md +++ b/README.md @@ -47,7 +47,7 @@ All the above packages are also saved in the file ``requirements.txt`` located i To directly use the pre-trained models we provide for download to separate your own songs, now skip directly to the [last section](#test), since the dataset is not needed in that case. -To reproduce the experiments in the paper (train all the models), you need to download the [ENST dataset](https://sigsep.github.io/datasets/musdb.html) and extract it into a folder of your choice. It should then have "drummer_1", "drummer_2" and "drummer_3" subfolders in it. +To reproduce the experiments in the paper (train all the models), you need to download the [ENST dataset](https://perso.telecom-paristech.fr/grichard/ENST-drums/) and extract it into a folder of your choice. It should then have "drummer_1", "drummer_2" and "drummer_3" subfolders in it. ### Set-up filepaths