| license: cc-by-nc-sa-4.0 | |
| The pretrained models for [Open-Unmix](https://huggingface.co/spaces/teamup-tech/Open-Unmix), mirrored from Zenodo, which serves them too slowly for a Space to start. Each folder is one model with one checkpoint per target, under the filenames `openunmix` expects. | |
| - `umxl/`: [UMX-L](https://doi.org/10.5281/zenodo.5069601), licensed CC-BY-NC-SA-4.0, so results cannot be used commercially and must be shared alike. | |
| - `umxhq/`: [UMX-HQ](https://doi.org/10.5281/zenodo.3370489), licensed MIT. | |
| The card declares CC-BY-NC-SA-4.0, the more restrictive of the two. The third published model, UMX, is left out: it is UMX-HQ trained on audio band-limited to 16 kHz, kept upstream for comparison with older results. | |