kenarsa
- Karma
- 0
- Created
- ()
- Submissions
- 0
- On-Device Real-Time Speech-to-Speech Translation [video] (youtube.com)
- Animating Ptolemy's Equant with Python, SVG, and CSS (rhodesmill.org)
-
Suppose you were going to create a compute-intensive cross-platform library in 2024. What would you use? C, C++, Rust, or something else?
- The importance of initialization and momentum in deep learning [pdf] (cs.toronto.edu)
-
Why MSVC still doesn't support C99 features like variable-length array (VLA)?
-
Why is WebAssembly not supporting 256/512 SIMD registers?
- Offline Voice Assistant on a Microcontroller with 192KB RAM (picovoice.ai)
- Arduino Voice Recognition in 10 Minutes or Less (picovoice.ai)
- DeepSpeech 60x Smaller, 9x faster, and 2x accuracy (github.com)
- 20MB is all you need for speech recognition (medium.com)
- 20MB is all you need for speech-to-text (medium.com)
- Octopus: Google Search for Voice (github.com)
- OctoTube: Voice Search for YouTube (medium.com)
- Yet Another Voice Activity Detection Engine (medium.com)
- Private Voice AI on Arduino (youtube.com)
- Offline Voice AI on Arduino (youtube.com)
- How We Added Raspberry Pi Support to Our .NET SDK (medium.com)
- Shush SSH, and Talk to Your Pi Instead (medium.com)