modal-vibevoice JacobLinCool · COMPLETED
Production-ready Modal deployment of Microsoft VibeVoice-ASR (9B). Multi-hour audio via VAD-aware chunking, cross-chunk speaker unification with CAM++, auto-batched multi-GPU inference. 15x realtime.
github.com/JacobLinCool/modal-vibevoice · ★ 2 · Forks 1 · Size 517 KB
SUMMARY
Technologies 7
Scored 7
Observed 7
Practices 6
Evidence 8
Skips 0
COVERAGE
Analyzed 22 files · 8 commits · 0 API calls
TECHNOLOGIES & DEPTH
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
TOML LANGUAGE Depth 70
1 files · PRODUCTION
Python LANGUAGE Depth 70
15 files · PRODUCTION
uv BUILD_TOOL Depth 80
1 files · CONFIGURATION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
FastAPI FRAMEWORK Depth 54
1 files · PRODUCTION
NumPy LIBRARY Depth 78
6 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · absentcontinuous_integration · absentcontainerization · absentlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-04-20
Last commit 2026-04-24
Active months 1
Commits 8