Skip to main content

A light-weight, streaming speech activity detection (SAD) module, designed for real-time speech-only classification

Project description

streamsad

streamsad is a streaming-oriented Speech Activity Detection (SAD) module that operates frame by frame, without requiring access to the full audio signal (unlike batch processing). Unlike simple energy-based Voice Activity Detection (VAD), it accurately detects human speech while ignoring music, background noise, and silence. Powered by an efficient ONNX model and a postprocessing algorithm inspired by WebRTC (using ring buffer smoothing), it runs entirely on the CPU with minimal overhead, making it ideal for real-time voice interfaces, ASR frontends, and low-resource deployments.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

streamsad-0.1.0.tar.gz (256.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

streamsad-0.1.0-py3-none-any.whl (255.6 kB view details)

Uploaded Python 3

File details

Details for the file streamsad-0.1.0.tar.gz.

File metadata

  • Download URL: streamsad-0.1.0.tar.gz
  • Upload date:
  • Size: 256.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.12

File hashes

Hashes for streamsad-0.1.0.tar.gz
Algorithm Hash digest
SHA256 4093fc096558055d164ac02686ce81f1472c84c6f3efdd300f48f7a9256c3bb7
MD5 dbd29a12b2d2907a3c7f04d0804ef447
BLAKE2b-256 38b6fba0d997168de8f951f83ebe81b0883e47a78fe0d1efd0d62c0f1f632342

See more details on using hashes here.

File details

Details for the file streamsad-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: streamsad-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 255.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.12

File hashes

Hashes for streamsad-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 de311704e80a322bb590a664dc46c083c4bbd0ce91657674c67a3d8270b8d2b5
MD5 54763eb841d6765b14967d75f93cfa58
BLAKE2b-256 d93fafb31b9a06fe79f40bcf92c3b738fe9106146d19252be9693d9d0d11b3b9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page