Asteroid model JorisCos/ConvTasNet_Libri2Mix_sepclean_16k


This model was trained by Joris Cosentino using the librimix recipe in Asteroid. It was trained on the sep_clean task of the Libri2Mix dataset.

Training config:

    n_src: 2
    sample_rate: 16000
    segment: 3
    task: sep_clean
    train_dir: data/wav16k/min/train-360
    valid_dir: data/wav16k/min/dev
    kernel_size: 32
    n_filters: 512
    stride: 16
    bn_chan: 128
    hid_chan: 512
    mask_act: relu
    n_blocks: 8
    n_repeats: 3
    skip_chan: 128
    lr: 0.001
    optimizer: adam
    weight_decay: 0.0
    batch_size: 6
    early_stop: true
    epochs: 200
    half_lr: true
    num_workers: 4

Results :

On Libri2Mix min test set :

si_sdr: 15.243671356901526
si_sdr_imp: 15.243034178473609
sdr: 15.668108919568112
sdr_imp: 15.578229918028036
sir: 25.295100756629957
sir_imp: 25.205219921301754
sar: 16.307682590197313
sar_imp: -51.64989963759405
stoi: 0.9394951175291422
stoi_imp: 0.22640192740016568

License notice:

This work "ConvTasNet_Libri2Mix_sepclean_16k" is a derivative of LibriSpeech ASR corpus by Vassil Panayotov, used under CC BY 4.0. "ConvTasNet_Libri2Mix_sepclean_16k" is licensed under Attribution-ShareAlike 3.0 Unported by Cosentino Joris.

Downloads last month
Hosted inference API

Inference API has been turned off for this model.