Feedback Is Trust: What We’re Learning While Designing Citra Voice There is a stage every product hits where the architecture is strong, the features work, and the experience still feels unfinished. That is where Citra Voice is right now, and it has taught us something important: A technically correct system can still feel untrustworthy if the interface doesn’t make system state legible to humans.…
Two Ways a Machine Can Listen: Qwen3-ASR vs Voxtral Realtime A detailed, source-checked architectural comparison of two speech-to-text systems — one centered on segment-style decoding, one designed for native realtime decoding. 1. Why This Comparison Matters This article compares two open ASR systems that target similar use cases but are architecturally very different: Qwen3-ASR-0.6B (Qwen)…
Whisper Notes from My Mac (September 2025) I spent the past few days gluing together a speech‑to‑text workflow on my Apple Silicon MacBook (macOS 26.0, Python 3.12). Most of what follows is a log of what actually happened: which warnings popped up, how I worked around them, and why I eventually leaned on whisper.cpp. I’m keeping this grounded so I (or anyone else) can repeat the steps later…
A comprehensive analysis tracing the evolution of attention mechanisms from bag-of-words models to FlashAttention, examining the mathematical foundations and interdisciplinary connections that enabled modern AI.
Short notes - pointers to programming for speed and efficiency, leveraging hardware-specific features available on ARM Apple Silicon. MacOS-focused at most places, although ideas are easy to generalise.
Chapter-wise notes for <a href=' https://www.manning.com/books/deep-learning-with-python-second-edition '>Deep Learning with Python</a> with Python and Clojure code samples. The book is not done. These notes are evolving as I get deeper both into the book and the accompanying code.
It's always useful to have some nice logging when writing code. Simple logging and exception handling samples to make it a bit easier for the developer.