Skip to content

edgeimpulseaudioinfer.md

Latest commit

 

History

History
88 lines (73 loc) · 2.32 KB

edgeimpulseaudioinfer.md

File metadata and controls

88 lines (73 loc) · 2.32 KB
Raw

edgeimpulseaudioinfer

Audio inference element that processes audio streams through Edge Impulse models.

Element Details

  • Long name: Edge Impulse Audio Inference
  • Class: Filter/Audio/AI
  • Description: Runs audio inference on Edge Impulse models (EIM)

Pad Templates

  • Sink pad (Always available): 
    audio/x-raw
  format: S16LE
  rate: [ 8000, 48000 ]
  channels: 1
  layout: interleaved
  • Source pad (Always available): 
    audio/x-raw
  format: S16LE
  rate: [ 8000, 48000 ]
  channels: 1
  layout: interleaved

Properties

  1. model-path (string):

    • Path to Edge Impulse model file
    • Default: null
    • Flags: readable, writable

  2. threshold (string):

    • Format: blockId.type=value
    • Types:
      • min_score: For object detection blocks
      • min_anomaly_score: For anomaly detection blocks
    • Examples:
      • 5.min_score=0.6: Set minimum confidence score for block 5
      • 4.min_anomaly_score=0.35: Set minimum anomaly score for block 4
    • Default: ""
    • Flags: readable, writable

Key Features

  • Accepts S16LE mono audio at 8-48kHz
  • Passes audio through unchanged
  • Performs inference when model is loaded
  • Attaches InferenceResultMeta to each buffer
  • Emits inference results as bus messages (see Public API)

Example Pipelines

# FFI mode (default)
gst-launch-1.0 autoaudiosrc ! \
    capsfilter caps="audio/x-raw,format=F32LE" ! \
    audioconvert ! \
    audioresample ! \
    capsfilter caps="audio/x-raw,format=S16LE,channels=1,rate=16000,layout=interleaved" ! \
    edgeimpulseaudioinfer ! \
    audioconvert ! \
    audioresample ! \
    capsfilter caps="audio/x-raw,format=F32LE,channels=2,rate=44100" ! \
    autoaudiosink

# EIM mode (legacy)
gst-launch-1.0 autoaudiosrc ! \
    capsfilter caps="audio/x-raw,format=F32LE" ! \
    audioconvert ! \
    audioresample ! \
    capsfilter caps="audio/x-raw,format=S16LE,channels=1,rate=16000,layout=interleaved" ! \
    edgeimpulseaudioinfer model-path=<path-to-model> ! \
    audioconvert ! \
    audioresample ! \
    capsfilter caps="audio/x-raw,format=F32LE,channels=2,rate=44100" ! \
    autoaudiosink

Debugging

GST_DEBUG=edgeimpulseaudioinfer:4 gst-launch-1.0 ...