同步操作将从 huqingli/Conv-TasNet 强制同步,此操作会覆盖自 Fork 仓库以来所做的任何修改,且无法恢复!!!
确定后同步将在后台操作,完成时将刷新页面,请耐心等待。
:bangbang:new:bangbang:: Updated model code, added code for skip connection section.
:bangbang:notice:bangbang:: Training Batch size setting 8/16
:bangbang:notice:bangbang:: The implementation of another article optimizing Conv-TasNet has been open sourced in "Deep-Encoder-Decoder-Conv-TasNet".
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation Pytorch's Implement
Luo Y, Mesgarani N. Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech Separation[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019, 27(8): 1256-1266.
python train.py ./option/train/train.yml
Inference Command (Use this command if you need to test a large number of audio files.)
python Separation.py -mix_scp 1.scp -yaml ./config/train/train.yml -model best.pt -gpuid [0,1,2,3,4,5,6,7] -save_path ./checkpoint
Inference Command (Use this command if you need to test a single audio files.)
python Separation_wav.py -mix_wav 1.wav -yaml ./config/train/train.yml -model best.pt -gpuid [0,1,2,3,4,5,6,7] -save_path ./checkpoint
N | L | B | H | Sc | P | X | R | Normalization | Causal | Receptive field | Model Size | SI-SNRi | SDRi |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
128 | 40 | 128 | 256 | 128 | 3 | 7 | 2 | gLN | x | 1.28 | 1.5M | 13.0 | 13.3 |
256 | 40 | 128 | 256 | 128 | 3 | 7 | 2 | gLN | x | 1.28 | 1.5M | 13.1 | 13.4 |
512 | 40 | 128 | 256 | 128 | 3 | 7 | 2 | gLN | x | 1.28 | 1.7M | 13.3 | 13.6 |
512 | 40 | 128 | 256 | 256 | 3 | 7 | 2 | gLN | x | 1.28 | 2.4M | 13.0 | 13.3 |
512 | 40 | 128 | 512 | 128 | 3 | 7 | 2 | gLN | x | 1.28 | 3.1M | 13.3 | 13.6 |
512 | 40 | 128 | 512 | 512 | 3 | 7 | 2 | gLN | x | 1.28 | 6.2M | 13.5 | 13.8 |
512 | 40 | 256 | 256 | 256 | 3 | 7 | 2 | gLN | x | 1.28 | 3.2M | 13.0 | 13.3 |
512 | 40 | 256 | 512 | 256 | 3 | 7 | 2 | gLN | x | 1.28 | 6.0M | 13.4 | 13.7 |
512 | 40 | 256 | 512 | 512 | 3 | 7 | 2 | gLN | x | 1.28 | 8.1M | 13.2 | 13.5 |
512 | 40 | 128 | 512 | 128 | 3 | 6 | 4 | gLN | x | 1.27 | 5.1M | 14.1 | 14.4 |
512 | 40 | 128 | 512 | 128 | 3 | 4 | 6 | gLN | x | 0.46 | 5.1M | 13.9 | 14.2 |
512 | 40 | 128 | 512 | 128 | 3 | 8 | 3 | gLN | x | 3.83 | 5.1M | 14.5 | 14.8 |
512 | 32 | 128 | 512 | 128 | 3 | 8 | 3 | gLN | x | 3.06 | 5.1M | 14.7 | 15.0 |
512 | 16 | 128 | 512 | 128 | 3 | 8 | 3 | gLN | x | 1.53 | 5.1M | 15.3 | 15.6 |
512 | 16 | 128 | 512 | 128 | 3 | 8 | 3 | cLN | √ | 1.53 | 5.1M | 10.6 | 11.0 |
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。