DPTNet_Libri1Mix_enhsingle_16k

JorisCos/DPTNet_Libri1Mix_enhsingle_16k

DPTNet_Libri1Mix_enhsingle_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

0% of all-time downloads

All-time downloads

406K

Public

Repo size

11.4 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin11.4 MB · 100%

At a glance

Task: Audio-to-Audio
Library: asteroid
License: cc-by-sa-4.0
Access: Public
Created: Mar 2, 2022
Updated: Sep 23, 2021
SHA: 935f441c

Datasets

Spaces

AllenIversonGPT/JorisCos-DPTNet_Libri1Mix_enhsingle_16k

Model card

From the Hugging Face model README

Asteroid model `JorisCos/DPTNet_Libri1Mix_enhsignle_16k`

Description:

This model was trained by Joris Cosentino using the librimix 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-360
  valid_dir: data/wav16k/min/dev
filterbank:
  kernel_size: 16
  n_filters: 64
  stride: 8
masknet:
  bidirectional: true
  chunk_size: 100
  dropout: 0
  ff_activation: relu
  ff_hid: 256
  hop_size: 50
  in_chan: 64
  mask_act: sigmoid
  n_repeats: 2
  n_src: 1
  norm_type: gLN
  out_chan: 64
optim:
  lr: 0.001
  optimizer: adam
  weight_decay: 1.0e-05
scheduler:
  d_model: 64
  steps_per_epoch: 10000
training:
  batch_size: 4
  early_stop: true
  epochs: 200
  gradient_clipping: 5
  half_lr: true
  num_workers: 4

Results:

On Libri1Mix min test set :

si_sdr: 14.829670037349064
si_sdr_imp: 11.379888731489366
sdr: 15.395712644737149
sdr_imp: 11.893049845524112
sir: Infinity
sir_imp: NaN
sar: 15.395712644737149
sar_imp: 11.893049845524112
stoi: 0.9301948391058859
stoi_imp: 0.13427501556534832

License notice:

This work "DPTNet_Libri1Mix_enhsignle_16k" 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). "DPTNet_Libri1Mix_enhsignle_16k" is licensed under Attribution-ShareAlike 3.0 Unported by Joris Cosentino

Task: Audio-to-Audio
Library: asteroid
License: cc-by-sa-4.0
Created: Mar 2, 2022
Updated: Sep 23, 2021