BestHub
Sign in
Tagged articles

STT

2 articles · Page 1 of 1
Weekly Large Model Application
Weekly Large Model Application
Jul 25, 2026 · Artificial Intelligence

How Pipeline Parallelism Cuts AI Voice Latency Below 700 ms

The article explains that keeping end‑to‑end voice‑assistant latency under 700 ms requires a co‑designed pipeline—streaming STT, speculative LLM, and streaming TTS—rather than faster individual models, and it details concrete component choices, budget allocations, and common pitfalls.

AI voiceLLMSTT
0 likes · 9 min read
How Pipeline Parallelism Cuts AI Voice Latency Below 700 ms
Open Source Linux
Open Source Linux
Nov 14, 2023 · Operations

Understanding Network Virtualization: VXLAN, NVGRE, STT, and SPBM Explained

This article explains how network virtualization decouples logical and physical networks, introduces Underlay and Overlay architectures, and compares four major overlay protocols—VXLAN, NVGRE, STT, and SPBM—highlighting their mechanisms and benefits for modern data‑center design.

Data Center NetworkingNVGRENetwork Virtualization
0 likes · 10 min read
Understanding Network Virtualization: VXLAN, NVGRE, STT, and SPBM Explained