Intel/apollo_jusperlee_openvino

Apollo (trained by @JusperLee) OpenVINO Model

This repo stores OpenVINO(TM) models in IR format that are used to perform Music Restoration.

The OpenVINO IRs (.xml, .bin files) stored here have been converted from @JusperLee's model checkpoint (pytorch_model.bin) from here: https://huggingface.co/JusperLee/Apollo

The configuration file used is from here: https://github.com/ZFTurbo/Music-Source-Separation-Training/blob/main/configs/config_apollo.yaml

Also, please see https://huggingface.co/JusperLee/Apollo for more information about this model.

To better support a range of OpenVINO-supported devices, the forward method from original pytorch model was sliced to remove the STFT / iSTFT functions.

The apollo_fwd.xml / .bin OpenVINO IR, stored in this repo, is a conversion of the modified pytorch model to OpenVINO format.

The OpenVINO IRs are intended to be used with the set of OpenVINO-based AI plugins for Audacity(R), here: https://github.com/intel/openvino-plugins-ai-audacity

Citations:

@article{li2024apollo,
  title={Apollo: Band-sequence Modeling for High-Quality Music Restoration in Compressed Audio},
  author={Li, Kai and Luo, Yi},
  journal={xxxxxx},
  year={2024}
}

Intel’s Human Rights Disclaimer:

Intel is committed to respecting human rights and avoiding complicity in human rights abuses. See Intel's Global Human Rights Principles. Intel's products and software are intended only to be used in applications that do not cause or contribute to a violation of an internationally recognized human right.