Edge-Speaker-Identification-System mahajialirezaei · PARTIAL
Edge-optimized speaker verification system built with Python 3.12, FastAPI, and ONNX Runtime. Uses a ResNet34 x-vector model (sherpa-onnx) for offline, low-latency speaker identification and enrollment. Runs with ~120MB RAM and ~180ms inference on edge devices like Raspberry Pi 4.
github.com/mahajialirezaei/Edge-Speaker-Identification-System · ★ 0 · Forks 0 · Size 3.5 MB
SUMMARY
Technologies 10
Scored 9
Observed 9
Practices 6
Evidence 11
Skips 1
COVERAGE
Analyzed 31 files · 65 commits · 0 API calls
TECHNOLOGIES & DEPTH
Dockerfile LANGUAGE Depth 70
1 files · PRODUCTION
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
YAML LANGUAGE Depth 70
2 files · PRODUCTION
Python LANGUAGE Depth 70
14 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
FastAPI FRAMEWORK Depth 66
2 files · PRODUCTION, TEST
HTTPX LIBRARY Depth —
0 files · config only
NumPy LIBRARY Depth 81
10 files · PRODUCTION, TEST
Uvicorn LIBRARY Depth 45
1 files · PRODUCTION
pytest TESTING Depth 45
3 files · TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · observedlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-06-30
Last commit 2026-07-04
Active months 2
Commits 65