Intel/versatile_audio_super_resolution_openvino

Versatile Audio Super Resolution OpenVINO(TM) Models

This repo stores Audio Super Resolution (and related) models, and other collateral that have been ported to OpenVINO IR format, from this GitHub project: https://github.com/haoheliu/versatile_audio_super_resolution

These models are used to run Super Resolution feature within this project: https://github.com/intel/openvino-plugins-ai-audacity

Description of collateral stored in Files and versions tab

• versatile_audio_sr_base_openvino_models.zip

  • audio_sr_decoder OpenVINO IR (and supporting files)
  • audio_sr_encoder OpenVINO IR (and supporting files)
  • vae_feature_extract OpenVINO IR
  • vocoder OpenVINO IR

• versatile_audio_sr_ddpm_basic_openvino_models.zip

  • 'base' ddpm OpenVINO IR

• versatile_audio_sr_ddpm_speech_openvino_models.zip

  • 'speech' ddpm OpenVINO IR

Details about source of these models:

All of the OpenVINO IR models stored here were converted from this GitHub project: https://github.com/haoheliu/versatile_audio_super_resolution

Citation:

@article{liu2023audiosr,
  title={{AudioSR}: Versatile Audio Super-resolution at Scale},
  author={Liu, Haohe and Chen, Ke and Tian, Qiao and Wang, Wenwu and Plumbley, Mark D},
  journal={arXiv preprint arXiv:2309.07314},
  year={2023}
}

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.