Real-Time-Speetch-Saparation-Model-Toolkit genius-0963 · COMPLETED
A PyTorch-based toolkit for real-time, speaker-independent speech separation using TasNet and DPRNN. Supports causal configs, RNN variants, and PIT loss with SI-SNR. Optimized for low-latency (<100ms) inference and high-quality audio separation. Ideal for research and real-time audio apps.
github.com/genius-0963/Real-Time-Speetch-Saparation-Model-Toolkit · ★ 1 · Forks 0 · Size 25.6 MB
SUMMARY
Technologies 14
Scored 14
Observed 14
Practices 6
Evidence 16
Skips 0
COVERAGE
Analyzed 1423 files · 12 commits · 0 API calls
TECHNOLOGIES & DEPTH
JSON LANGUAGE Depth 70
20 files · PRODUCTION
Shell LANGUAGE Depth 70
14 files · PRODUCTION
Markdown LANGUAGE Depth 70
127 files · PRODUCTION
TOML LANGUAGE Depth 70
1 files · PRODUCTION
YAML LANGUAGE Depth 70
279 files · PRODUCTION
Python LANGUAGE Depth 70
694 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 81
101 files · PRODUCTION, TEST
Redis CACHE Depth 69
2 files · CONFIGURATION
Requests LIBRARY Depth 81
7 files · PRODUCTION
TypeScript LANGUAGE Depth 81
38 files · PRODUCTION, TEST
pandas LIBRARY Depth 74
19 files · PRODUCTION
pytest TESTING Depth 78
21 files · PRODUCTION, TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · absentlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2025-05-28
Last commit 2026-10-01
Active months 4
Commits 12