cjm-media-plugin-silero-vad 0.0.5

A local, persistent Voice Activity Detection (VAD) worker for the cjm-plugin-system that provides high-accuracy speech segmentation using Silero VAD with SQLite result caching.

cjm-media-plugin-silero-vad

Install

pip install cjm_media_plugin_silero_vad

Project Structure

nbs/
├── meta.ipynb   # Metadata introspection for the Silero VAD plugin used by cjm-ctl to generate the registration manifest.
└── plugin.ipynb # Plugin implementation for Voice Activity Detection using Silero VAD with SQLite result caching.

Total: 2 notebooks

Module Dependencies

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

    plugin --> meta

1 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 Silero VAD plugin used by cjm-ctl to generate the registration manifest.

Import

from cjm_media_plugin_silero_vad.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
    cjm_data_dir = os.environ.get("CJM_DATA_DIR")
    
    # Plugin data directory
    plugin_name = "cjm-media-plugin-silero-vad"
    if cjm_data_dir
    "Return metadata required to register this plugin with the PluginManager."

Silero VAD Plugin (plugin.ipynb)

Plugin implementation for Voice Activity Detection using Silero VAD with SQLite result caching.

Import

from cjm_media_plugin_silero_vad.plugin import (
    SileroVADConfig,
    SileroVADPlugin
)

Classes

@dataclass
class SileroVADConfig:
    "Configuration for Silero VAD parameters."
    
    threshold: float = field(...)
    min_speech_duration_ms: int = field(...)
    min_silence_duration_ms: int = field(...)
    speech_pad_ms: int = field(...)
    sampling_rate: int = field(...)
    use_onnx: bool = field(...)

class SileroVADPlugin:
    def __init__(self):
        """Initialize the Silero VAD plugin."""
        self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
        self.config: SileroVADConfig = None
    "Voice Activity Detection plugin using Silero VAD."
    
    def __init__(self):
            """Initialize the Silero VAD plugin."""
            self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
            self.config: SileroVADConfig = None
        "Initialize the Silero VAD plugin."
    
    def name(self) -> str:  # Plugin name identifier
            """Get the plugin name identifier."""
            return "silero-vad"
        
        @property
        def version(self) -> str:  # Plugin version string
        "Get the plugin name identifier."
    
    def version(self) -> str:  # Plugin version string
            """Get the plugin version string."""
            return "1.0.0"
        
        @property
        def supported_media_types(self) -> List[str]:  # Supported media types
        "Get the plugin version string."
    
    def supported_media_types(self) -> List[str]:  # Supported media types
            """Get the list of supported media types."""
            return ["audio", "video"]
    
        def get_current_config(self) -> Dict[str, Any]:  # Current configuration as dictionary
        "Get the list of supported media types."
    
    def get_current_config(self) -> Dict[str, Any]:  # Current configuration as dictionary
            """Return current configuration state."""
            return config_to_dict(self.config) if self.config else {}
    
        def get_config_schema(self) -> Dict[str, Any]:  # JSON Schema for configuration
        "Return current configuration state."
    
    def get_config_schema(self) -> Dict[str, Any]:  # JSON Schema for configuration
            """Return JSON Schema for UI generation."""
            return dataclass_to_jsonschema(SileroVADConfig)
    
        def initialize(
            self,
            config: Optional[Any] = None  # Configuration dataclass, dict, or None
        ) -> None
        "Return JSON Schema for UI generation."
    
    def initialize(
            self,
            config: Optional[Any] = None  # Configuration dataclass, dict, or None
        ) -> None
        "Initialize or re-configure the plugin (idempotent)."
    
    def execute(
            self,
            media_path: Union[str, Path],  # Path to media file to analyze
            force: bool = False,           # If True, ignore cache and re-run
            **kwargs                       # Override config parameters for this run
        ) -> MediaAnalysisResult:  # Analysis result with detected speech segments
        "Run VAD on the audio file."
    
    def is_available(self) -> bool:  # True if Silero VAD is available
            """Check if Silero VAD is available."""
            return SILERO_AVAILABLE
    
        def cleanup(self) -> None
        "Check if Silero VAD is available."
    
    def cleanup(self) -> None:
            """Clean up resources."""
            if self._model is not None
        "Clean up resources."