小行星模型 JorisCos/DPTNet_Libri1Mix_enhsignle_16k

描述:

此模型由Joris Cosentino使用librimix配方在 Asteroid 上进行训练。它是在Libri1Mix数据集的enh_single任务上训练的。

训练配置:

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

结果:

在Libri1Mix min测试集上:

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

许可通知:

这项工作"DPTNet_Libri1Mix_enhsignle_16k"是由Joris Cosentino根据 LibriSpeech ASR corpus 衍生而来，使用Vassil Panayotov的许可，仅用于 CC BY 4.0 下的研究; 根据 Whisper.ai 的The WSJ0 Hipster Ambient Mixtures数据集使用许可，仅用于 CC BY-NC 4.0 下的研究。"DPTNet_Libri1Mix_enhsignle_16k"由Joris Cosentino根据 Attribution-ShareAlike 3.0 Unported 许可。