What should I build next for signspell?
Hey everyone — signspell (v2.0.0) is now on PyPI and I recently launched it on Product Hunt. It currently handles ASL fingerspelling (A–Z) recognition using MediaPipe hand landmarks + a TFLite LSTM model, and I also built Gesto Labeller (a desktop tool for capturing/labeling training data).
I'm trying to figure out the next milestone and would love input from people actually using or evaluating it:
Would full word/phrase-level ASL recognition (beyond fingerspelling) be more valuable than polishing fingerspelling accuracy further?
Is real-time performance/latency on lower-end devices a bigger blocker than accuracy right now?
Should the next priority be broader sign language support (BSL, ISL, etc.) or going deeper on ASL first?
Any specific integrations you'd want (e.g. web SDK, mobile bindings, browser extension) that would make signspell more usable in your projects?
Genuinely open to being told I'm focusing on the wrong thing — what's the gap you'd want filled next?
Replies
Have you tried it with cheap webcams yet??
Signspell
@ethan_marshall Yes,
It works well - regardless of the camera .
I can imaging developers having fun building on top of the SDK. I
Signspell
@brielle_marie Ofcourse .
@sundar_balamurugan Gesto Labeller is a pretty interesting part of this whole steup.
Signspell
@alice_hayes2 Yes,
Thanks for the POV.
I'm curious how this performs outside a controlled demo.
Signspell
@gideon_henry Yes.
I am looking for this .
Let us see how it performs.
latency on low-end devices, every time. we went through the same call on a real-time on-device model, and a slightly less accurate result that keeps up beats a smarter one that lags, people bail before they notice the model was right. how far behind is TFLite LSTM on a mid-range phone right now, frame drops or full-on lag
Signspell