--- license: cc-by-4.0 tags: - audio - panns - mirror --- # Cutpoint model mirror Mirror of model files that [Cutpoint](https://github.com/FerventOrange/cutpoint) downloads during `cutpoint setup`. These are unmodified copies. They're hosted here because the original source can be very slow. ## PANNs `panns/Cnn14_DecisionLevelMax_mAP=0.385.pth` - Source: Zenodo record [10.5281/zenodo.3987831](https://doi.org/10.5281/zenodo.3987831), "PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition (Pretrained Models)" - Authors: Qiuqiang Kong, Yin Cao, Turab Iqbal, Yuxuan Wang, Wenwu Wang, Mark D. Plumbley - License: [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), as on the original record - Paper: Kong et al., "PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition", IEEE/ACM TASLP 2020 ([arXiv:1912.10211](https://arxiv.org/abs/1912.10211)) - Size: 327,428,481 bytes - SHA-256: `dd3b4043a87d4ec13df8082c0fcfee3fb5084151808e47e060987a95eabdd142`