Downloads · 30 days
692
1% of all-time downloads
JorisCos/ConvTasNet_Libri2Mix_sepnoisy_16k
ConvTasNet_Libri2Mix_sepnoisy_16k is a audio-to-audio model from JorisCos. Use it for the audio-to-audio task on the model card, and read the license before you ship it in a product. It is set up for asteroid. The card lists the license as cc-by-sa-4.0.
Downloads · 30 days
692
1% of all-time downloads
All-time downloads
82.5K
Public
Repo size
20.4 MB
Likes
1
Public
Click a slice to open those files.
.bin20.4 MB · 100%
From the Hugging Face model README
JorisCos/ConvTasNet_Libri2Mix_sepnoisy_16kDescription:
This model was trained by Joris Cosentino using the librimix recipe in Asteroid.
It was trained on the sep_noisy task of the Libri2Mix dataset.
Training config:
data:
n_src: 2
sample_rate: 16000
segment: 3
task: sep_noisy
train_dir: data/wav16k/min/train-360
valid_dir: data/wav16k/min/dev
filterbank:
kernel_size: 32
n_filters: 512
stride: 16
masknet:
bn_chan: 128
hid_chan: 512
mask_act: relu
n_blocks: 8
n_repeats: 3
n_src: 2
skip_chan: 128
optim:
lr: 0.001
optimizer: adam
weight_decay: 0.0
training:
batch_size: 6
early_stop: true
epochs: 200
half_lr: true
num_workers: 4
Results:
On Libri2Mix min test set :
si_sdr: 10.617130949793383
si_sdr_imp: 12.551811412989263
sdr: 11.231867464482065
sdr_imp: 13.059765009747343
sir: 24.461138352988346
sir_imp: 24.371856452307703
sar: 11.5649982725426
sar_imp: 4.662525705768228
stoi: 0.8701085138712695
stoi_imp: 0.2245418019822898
License notice:
This work "ConvTasNet_Libri2Mix_sepnoisy_16k" is a derivative of LibriSpeech ASR corpus by Vassil Panayotov, used underCC BY 4.0; of The WSJ0 Hipster Ambient Mixtures dataset by Whisper.ai, used under CC BY-NC 4.0 (Research only). "ConvTasNet_Libri2Mix_sepnoisy_16k" is licensed under Attribution-ShareAlike 3.0 Unported by Joris Cosentino