Plugin

Demucs v4 audio source separation plugin — provides vocals extraction for removing background noise and music from speech audio.

Imports

Configuration

---

DemucsPluginConfig

def DemucsPluginConfig(
    model:str='htdemucs', device:str='auto', shifts:int=1, overlap:float=0.25, segment:Optional=None,
    save_other_stems:bool=False, output_format:str='wav'
)->None:

Configuration for the Demucs processing plugin.

Plugin Class

---

DemucsProcessingPlugin

def DemucsProcessingPlugin(
    
):

Demucs v4 source separation plugin for vocals extraction.

---

DemucsProcessingPlugin.prefetch

def prefetch(
    
)->None:

CR-4 (SG-19): eagerly load the model so the first execute() doesn’t pay the download/load cost. Idempotent via _load_model’s None-guard.

---

DemucsProcessingPlugin.on_disable

def on_disable(
    
)->None:

CR-2: release the GPU model when the operator disables the plugin (the worker stays alive); lazy reload on the next execute after re-enable.

---

DemucsProcessingPlugin.cleanup

def cleanup(
    
)->None:

Clean up plugin resources.

---

DemucsProcessingPlugin.is_available

def is_available(
    
)->bool: # Whether the plugin can run

Check if the plugin is available on this system.