| pipeline_tag: audio-to-audio | |
| tags: | |
| - roformer | |
| - speech | |
| Specially trained to separate the speaker's voice from background music that contains vocals. |
| pipeline_tag: audio-to-audio | |
| tags: | |
| - roformer | |
| - speech | |
| Specially trained to separate the speaker's voice from background music that contains vocals. |