DNN-based source separation

A PyTorch implementation of DNN-based source separation.

New information

• v0.7.2
  • Update jupyter notebooks.

Model

Modules

Method related to training

Example

LibriSpeech example using Conv-TasNet

You can check other tutorials in <REPOSITORY_ROOT>/egs/tutorials/.

0. Preparation

cd <REPOSITORY_ROOT>/egs/tutorials/common/
. ./prepare_librispeech.sh \
--librispeech_root <LIBRISPEECH_ROOT> \
--n_sources <#SPEAKERS>

1. Training

cd <REPOSITORY_ROOT>/egs/tutorials/conv-tasnet/
. ./train.sh \
--exp_dir <OUTPUT_DIR>

If you want to resume training,

. ./train.sh \
--exp_dir <OUTPUT_DIR> \
--continue_from <MODEL_PATH>

2. Evaluation

cd <REPOSITORY_ROOT>/egs/tutorials/conv-tasnet/
. ./test.sh \
--exp_dir <OUTPUT_DIR>

3. Demo

cd <REPOSITORY_ROOT>/egs/tutorials/conv-tasnet/
. ./demo.sh

Pretrained Models

You need gdown to download pretrained models.

pip install gdown

You can load pretrained models.

from models.conv_tasnet import ConvTasNet

model = ConvTasNet.build_from_pretrained(task="musdb18", sample_rate=44100, target="vocals")

See PRETRAINED.md, egs/tutorials/hub/pretrained.ipynb or click for details.

Time Domain Wrappers for Time-Frequency Domain Models

See egs/tutorials/hub/time-domain_wrapper.ipynb or click .

Speech Separation by Pretrained Models

See egs/tutorials/hub/speech-separation.ipynb or click .

Music Source Separation by Pretrained Models

See egs/tutorials/hub/music-source-separation.ipynb or click .

If you want to separate your own music file, see below:

• MMDenseLSTM: See egs/tutorials/mm-dense-lstm/separate_music.ipynb or click .
• Conv-TasNet: See egs/tutorials/conv-tasnet/separate_music.ipynb or click .
• UMX: See egs/tutorials/umx/separate_music.ipynb or click .
• X-UMX: See egs/tutorials/x-umx/separate_music.ipynb or click .
• D3Net: See egs/tutorials/d3net/separate_music.ipynb or click .