模型:
mpariente/ConvTasNet_Libri1Mix_enhsingle_8k
许可:
cc-by-sa-4.0从Zenodo中导入此模型 model page .
此模型是由Brij Mohan使用Asteroid中的Librimix/ConvTasNet配方进行训练的。它是在Libri3Mix数据集的enh_single任务上进行训练的。
data: n_src: 1 sample_rate: 8000 segment: 3 task: enh_single train_dir: data/wav8k/min/train-360 valid_dir: data/wav8k/min/dev filterbank: kernel_size: 16 n_filters: 512 stride: 8 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 training: batch_size: 24 early_stop: True epochs: 200 half_lr: True
si_sdr: 14.783675142685572 si_sdr_imp: 11.464625198953202 sdr: 15.497505907983102 sdr_imp: 12.07230150154914 sar: 15.497505907983102 sar_imp: 12.07230150154914 stoi: 0.9270030254700518 stoi_imp: 0.1320547197597893
此工作“ConvTasNet_Libri1Mix_enhsingle_8k”是基于 LibriSpeech ASR corpus 由 Vassil Panayotov 创作的,使用 CC BY 4.0 授权。 "ConvTasNet_Libri1Mix_enhsingle_8k"受Manuel Pariente的 Attribution-ShareAlike 3.0 Unported 许可。