I Run a 55 M parameter speech to text Model on esp 32

I Run a 55 M parameter speech to text Model on esp 32

Updated 1 hour ago
Project Details
Active
0
0
0%

Offline speech-to-text on a microcontroller: Cactus Compute's Whistle model cut to fit 16 MB flash, with a from-scratch C engine. No cloud.


Similar Projects

Cloud-based Coding Plugin: Real-time Optimization Suggestions from AI Models for Your Web Pages
Cloud-based Coding Plugin: Real-time Optimization Suggestions from AI Models for Your Web Pages

工作台开任务、跑云端 Agent,浏览器插件对着真实页面提优化建议。租户 RBAC、GitLab SSO、KYC...

2
1
Airy TTS – A fast, low-cost TTS API built for full-response latency
Airy TTS – A fast, low-cost TTS API built for full-response latency

Airy Studio offers free text-to-speech for creators. Airy API is the fastest, cheapest TTS...

1
0
I built self-healing GitHub Actions runners they fix flaky CI failures mid-run
I built self-healing GitHub Actions runners they fix flaky CI failures mid-run

Managed GitHub Actions runners that repair failing builds mid-run. One line to switch, $0....

1
1
Built a free invoice generator that runs 100% in your browser (no signup, no server)
Built a free invoice generator that runs 100% in your browser (no signup, no server)

Free invoice generator that never uploads your data. No signup, no server — fill in detail...

1
2
I created a tool to make studying pdf textbooks easier
I created a tool to make studying pdf textbooks easier

A PDF study tool for Mac. Take notes in textbooks and pick up where you left off. Try all...

1
0
🚨 Think your website is fine? Run these 30 checks first
🚨 Think your website is fine? Run these 30 checks first

Scan any website for security vulnerabilities, SEO issues, and performance problems. Get a...

1
0