Software Open Access

mhu-coder/ConvTasNet_Libri1Mix_enhsingle

Mathieu Hu

Description:

This model was trained by Mathieu Hu using the librimix/ConvTasNet recipe in Asteroid. It was trained on the enh_single task of the Libri1Mix dataset.

 

Training config:

  • data:
    • n_src: 1
    • sample_rate: 16000
    • segment: 3
    • task: enh_single
    • train_dir: data/wav16k/min/train-100
    • valid_dir: data/wav16k/min/dev
  • filterbank:
    • kernel_size: 16
    • n_filters: 512
    • stride: 8
  • main_args:
    • exp_dir: exp/train_convtasnet_f34664b9
    • help: None
  • masknet:
    • bn_chan: 128
    • hid_chan: 512
    • mask_act: relu
    • n_blocks: 8
    • n_repeats: 3
    • n_src: 1
    • skip_chan: 128
  • optim:
    • lr: 0.001
    • optimizer: adam
    • weight_decay: 0.0
  • positional arguments:
    • training:
      • batch_size: 2
      • early_stop: True
      • epochs: 200
      • half_lr: True
      • num_workers: 4

     

    Results:

    • si_sdr: 13.938355526049932
    • si_sdr_imp: 10.488574220190232
    • sdr: 14.567380104207393
    • sdr_imp: 11.064717304994337
    • sir: inf
    • sir_imp: nan
    • sar: 14.567380104207393
    • sar_imp: 11.064717304994337
    • stoi: 0.9201010933251715
    • stoi_imp: 0.1241812697846321

     

    Versions:

    • torch_version: 1.5.0
    • pytorch_lightning_version: 0.7.6
    • asteroid_version: 0.2.1

     

    License notice:

    This work "ConvTasNet_Libri1Mix_enhsingle" is a derivative of LibriSpeech ASR corpus by Vassil Panayotov, used under CC BY 4.0; of The WSJ0 Hipster Ambient Mixtures dataset by Whisper.ai, used under CC BY-NC 4.0 (Research only). "ConvTasNet_Libri1Mix_enhsingle" is licensed under Attribution-ShareAlike 3.0 Unported by Mathieu Hu.
    Files (20.1 MB)
    Name Size
    model.pth
    md5:15fbaa73b30e1442ca1d0573de3a45e2     		20.1 MB Download
    703
    1,350
    views
    downloads
    All versions This version
    Views 703702
    Downloads 1,3501,350
    Data volume 27.1 GB27.1 GB
    Unique views 598597
    Unique downloads 728728
    More info on how stats are collected.
    Indexed in
    Publication date:
    December 2, 2020
    DOI:
    10.5281/zenodo.4301955

    Zenodo DOI Badge

    DOI 

    10.5281/zenodo.4301955

    Markdown 

    [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.4301955.svg)](https://doi.org/10.5281/zenodo.4301955)

    reStructedText 

    .. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.4301955.svg
   :target: https://doi.org/10.5281/zenodo.4301955

    HTML 

    <a href="https://doi.org/10.5281/zenodo.4301955"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.4301955.svg" alt="DOI"></a>

    Image URL 

    https://zenodo.org/badge/DOI/10.5281/zenodo.4301955.svg

    Target URL 

    https://doi.org/10.5281/zenodo.4301955

    Keyword(s):
    Asteroid audio source separation Libri1Mix enh_single ConvTasNet pretrained model
    Communities:
    License (for files):
    Creative Commons Attribution Share Alike 3.0 Unported

    Versions

    Version 1 10.5281/zenodo.4301955 Dec 2, 2020
    Cite all versions? You can cite all versions by using the DOI 10.5281/zenodo.4301954. This DOI represents all versions, and will always resolve to the latest one. Read more.

    Share

    Cite as

    Export