</> HitReader
Blog Explore About

Tag: #speech-recognition

How Whistle Fits Offline Speech Recognition Into 16.9 MB
edge ai Oct 08, 2026 6 min read

How Whistle Fits Offline Speech Recognition Into 16.9 MB

Whistle packs seven-language, on-device speech recognition into 16.9 MB while providing transcripts, word timestamps, embeddings, and local voice-to-tool calls. This guide explains the compact audio pipeline, cached cross-attention, decoder ladder, and CPU-focused design behind it.

by ahsan
#edge ai #on-device ai #python #speech-recognition #tinyml
Speech Recognition and TTS in Under 500KB: How It Works on a Microcontroller
embedded ai Jul 19, 2026 1 min read

Speech Recognition and TTS in Under 500KB: How It Works on a Microcontroller

Speech on microcontrollers sounds impossible until you see the trick: use a narrow speech pipeline, quantized neural nets, streaming audio, and aggressive memory reuse. Moonshine Micro’s RP2350 demo is sized around ~470 KB RAM for VAD → STT → neural TTS.

by ahsan
#embedded-ml #microcontrollers #speech-recognition #tinyml #tts

Categories

  • artificial intelligence
  • machine learning
  • software engineering
  • cybersecurity
  • web development
  • developer tools
  • open source
  • embedded systems
Explore all →

Tags

#open-source #artificial intelligence #ai agents #privacy #cybersecurity #llm #machine learning #linux #large language models #rust #javascript #developer tools
Explore all →

© 2026 HitReader.

About Explore Terms Privacy Facebook