AkshathRaghav/tinyspeech

Code release for "TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices"

39
/ 100
Emerging

This project provides an efficient way to make speech recognition models run on tiny, low-power microcontrollers. It takes audio input and converts it into recognized speech, even on devices with very limited memory and processing power. This is ideal for embedded systems developers creating voice-controlled devices or IoT products.

No commits in the last 6 months.

Use this if you need to integrate accurate speech recognition into extremely resource-constrained edge devices, such as those with only 2KB of SRAM.

Not ideal if you are working with powerful cloud-based servers or devices with ample computational resources.

embedded-systems IoT voice-control edge-AI low-power-electronics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

21

Forks

4

Language

C

License

MIT

Last pushed

Jun 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/AkshathRaghav/tinyspeech"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.