SigSep: Open Resources for Audio Source Separation
Published February 20, 2023 | Version v1
Dataset Open

Open-Unmix-Pytorch LabelNoise

Creators

  • 1. SDX Challenge Org

Description

SDXDB21 LabelNoise Baseline

We split the training data into train and valid. For valid, the following songs were used:
bc1f2967-f834-43bd-aadc-95afc897cfe7
cc3e4991-6cce-40fe-a917-81a4fbb92ea6
ed90a89a-bf22-444d-af3d-d9ac3896ebd2
f4b735de-14b1-4091-a9ba-c8b30c0740a7
bc964128-da16-4e4c-af95-4d1211e78c70
cc7f7675-d3c8-4a49-a2d7-a8959b694004
f40ffd10-4e8b-41e6-bd8a-971929ca9138
The following commands were used to create the models:
OMP_NUM_THREADS=1 CUDA_VISIBLE_DEVICES=3 python train.py \

    --root /sdxdb23_labelnoise_v1.0       \
    --dataset trackfolder_fix                            \
    --target-file vocals.wav                             \
    --interferer-files bass.wav drums.wav other.wav      \
    --random-track-mix                                   \
    --lr-decay-patience 160                              \
    --source-augmentations gain channelswap 

OMP_NUM_THREADS=1 CUDA_VISIBLE_DEVICES=4 python train.py \

    --root /sdxdb23_labelnoise_v1.0       \
    --dataset trackfolder_fix                            \
    --target-file bass.wav                               \
    --interferer-files vocals.wav drums.wav other.wav    \
    --random-track-mix                                   \
    --lr-decay-patience 160                              \
    --source-augmentations gain channelswap 

OMP_NUM_THREADS=1 CUDA_VISIBLE_DEVICES=5 python train.py \

    --root /sdxdb23_labelnoise_v1.0       \
    --dataset trackfolder_fix                            \
    --target-file drums.wav                              \
    --interferer-files bass.wav vocals.wav other.wav     \
    --random-track-mix                                   \
    --lr-decay-patience 160                              \
    --source-augmentations gain channelswap
 

OMP_NUM_THREADS=1 CUDA_VISIBLE_DEVICES=7 python train.py \

    --root /sdxdb23_labelnoise_v1.0       \
    --dataset trackfolder_fix                            \
    --target-file other.wav                              \
    --interferer-files bass.wav drums.wav vocals.wav     \
    --random-track-mix                                   \
    --lr-decay-patience 160                              \
    --source-augmentations gain channelswap

 

Files

bass.json

Files (569.9 MB)

Name Size Download all
md5:2542191acbcde1397d5424ef989aeb97
106.8 MB Download
md5:77a662a899d8a44754e186deba99475e
32.7 kB Preview Download
md5:89df90073a90b416d0987349d4fc616f
35.6 MB Download
md5:0b2a2614eb81d0257ebf76a836b21c89
106.8 MB Download
md5:409b91cbe4b56df9e1b0b3c6fb912dfd
55.9 kB Preview Download
md5:39ad6f3d8dd70be3b033f4975cb5f8f3
35.6 MB Download
md5:e6364eb6778f2b348b096295b4218038
106.8 MB Download
md5:cb6d8170496a4a228a8e0fb83e8fab1d
42.4 kB Preview Download
md5:5d2013d498f8666958e12ea2bd44043c
35.6 MB Download
md5:60e9779dcefa367b800bdb72d9a91a3c
88 Bytes Preview Download
md5:80d6147c47bfd530b1e6bd5c900ab937
106.8 MB Download
md5:c66e1d390f2646e85b4cddc3faef6bd3
38.8 kB Preview Download
md5:442f4b5807df83f7b3274d4a392e6a05
35.6 MB Download