cjm-media-plugin-demucs 0.0.4

Demucs v4 audio source separation plugin for the cjm-plugin-system that provides vocals extraction for removing background noise and music from speech audio.

cjm-media-plugin-demucs

Install

pip install cjm_media_plugin_demucs

Project Structure

nbs/
├── meta.ipynb   # Metadata introspection for the Demucs plugin used by cjm-ctl to generate the registration manifest.
└── plugin.ipynb # Demucs v4 audio source separation plugin — provides vocals extraction for removing background noise and music from speech audio.

Total: 2 notebooks

Module Dependencies

graph LR
    meta["meta<br/>Metadata"]
    plugin["plugin<br/>Plugin"]

No cross-module dependencies detected.

CLI Reference

No CLI commands found in this project.

Module Overview

Detailed documentation for each module in the project:

Metadata (meta.ipynb)

Metadata introspection for the Demucs plugin used by cjm-ctl to generate the registration manifest.

Import

from cjm_media_plugin_demucs.meta import (
    get_plugin_metadata
)

Functions

def get_plugin_metadata() -> Dict[str, Any]:  # Plugin metadata for manifest generation
    """Return metadata required to register this plugin with the PluginManager."""
    # Fallback base path (current behavior for backward compatibility)
    base_path = os.path.dirname(os.path.dirname(sys.executable))
    
    # Use CJM config if available, else fallback to env-relative paths
    cjm_data_dir = os.environ.get("CJM_DATA_DIR")
    cjm_models_dir = os.environ.get("CJM_MODELS_DIR")
    
    # Plugin data directory
    plugin_name = "cjm-media-plugin-demucs"
    if cjm_data_dir
    "Return metadata required to register this plugin with the PluginManager."

Plugin (plugin.ipynb)

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

Import

from cjm_media_plugin_demucs.plugin import (
    DemucsPluginConfig,
    DemucsProcessingPlugin
)

Classes

@dataclass
class DemucsPluginConfig:
    "Configuration for the Demucs processing plugin."
    
    model: str = field(...)
    device: str = field(...)
    shifts: int = field(...)
    overlap: float = field(...)
    segment: Optional[int] = field(...)
    save_other_stems: bool = field(...)
    output_format: str = field(...)

class DemucsProcessingPlugin:
    def __init__(self):
        """Initialize the plugin."""
        self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
        self.config: Optional[DemucsPluginConfig] = None
    "Demucs v4 source separation plugin for vocals extraction."
    
    def __init__(self):
            """Initialize the plugin."""
            self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
            self.config: Optional[DemucsPluginConfig] = None
        "Initialize the plugin."
    
    def name(self) -> str:  # Plugin name identifier
            """Get the plugin name."""
            return "cjm-media-plugin-demucs"
        
        @property
        def version(self) -> str:  # Plugin version string
        "Get the plugin name."
    
    def version(self) -> str:  # Plugin version string
            """Get the plugin version."""
            from cjm_media_plugin_demucs import __version__
            return __version__
        
        @property
        def supported_media_types(self) -> List[str]:  # Supported media types
        "Get the plugin version."
    
    def supported_media_types(self) -> List[str]:  # Supported media types
            """Get supported media types."""
            return ["audio"]
        
        # ── Lifecycle ────────────────────────────────────────────────────
        
        def _apply_config(self,
                          config: Optional[Any] = None,  # Configuration dict or None for defaults
                         ) -> None
        "Get supported media types."
    
    def initialize(self,
                       config: Optional[Any] = None,  # Configuration dict or None for defaults
                      ) -> None
        "First-time setup. CR-4: config application factored into _apply_config; the
substrate's reconfigure path fires _release_model on a model/device change then
re-applies config."
    
    def prefetch(self) -> 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."""
            self._load_model()
    
        def on_disable(self) -> 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."
    
    def on_disable(self) -> 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."""
            self._release_model()
    
        def cleanup(self) -> 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."
    
    def cleanup(self) -> None:
            """Clean up plugin resources."""
            self._release_model()
            self.logger.info("Plugin cleaned up")
        
        def is_available(self) -> bool:  # Whether the plugin can run
        "Clean up plugin resources."
    
    def is_available(self) -> bool:  # Whether the plugin can run
            """Check if the plugin is available on this system."""
            try
        "Check if the plugin is available on this system."
    
    def get_config_schema(self) -> Dict[str, Any]:  # JSON Schema for UI forms
            """Return JSON Schema for the plugin configuration."""
            return dataclass_to_jsonschema(DemucsPluginConfig)
        
        def get_current_config(self) -> Dict[str, Any]:  # Current config as dict
        "Return JSON Schema for the plugin configuration."
    
    def get_current_config(self) -> Dict[str, Any]:  # Current config as dict
            """Return the current configuration."""
            return config_to_dict(self.config) if self.config else {}
        
        # ── Model Management ────────────────────────────────────────────
        
        def _load_model(self) -> None
        "Return the current configuration."
    
    def execute(self,
                    action: str = "separate_vocals",  # Action to perform
                    **kwargs
                   ) -> Dict[str, Any]:  # Action result
        "Dispatch to the `@plugin_action`-tagged handler for `action` (SG-44)."
    
    def get_info(self,
                     file_path: str,  # Path to audio file
                    ) -> MediaMetadata:  # File metadata
        "Get basic audio file metadata via ffprobe."
    
    def convert(self, input_path, output_format, **kwargs):
            """Not applicable for source separation."""
            raise PluginInputError(  # SG-47: typed input-validation; this method is
                # not applicable for this plugin domain.
                "convert is not supported by the Demucs plugin. "
                "Use 'separate_vocals' instead.",
                fields_invalid=["action"],
            )
        
        def extract_segment(self, input_path, start, end, output_path=None)
        "Not applicable for source separation."
    
    def extract_segment(self, input_path, start, end, output_path=None):
            """Not applicable for source separation."""
            raise PluginInputError(  # SG-47: typed input-validation; this method is
                # not applicable for this plugin domain.
                "extract_segment is not supported by the Demucs plugin. "
                "Use 'separate_vocals' instead.",
                fields_invalid=["action"],
            )
        
        # ── Core Action ──────────────────────────────────────────────────
        
        def _separate_vocals(self,
                             input_path: str,  # Path to audio file
                             output_dir: Optional[str] = None,  # Output directory (default: data_dir/vocals/)
                             output_format: Optional[str] = None,  # Output format override
                            ) -> Dict[str, Any]:  # Separation result
        "Not applicable for source separation."