Show HN: Sign language translation with smart glasses
Summary
Hand Wave is an open-source sign language recognition system for web and iOS, backed by a Python inference service, aiming to enable translation via smart glasses.
View Cached Full Text
Cached at: 08/08/26, 11:17 AM
aadisang/hand-wave
Source: https://github.com/aadisang/hand-wave
Hand Wave
Sign recognition for web and iOS, backed by a small Python inference service.
Setup
Requirements: pnpm 10.33+, Node 22+, Python 3.11/3.12, uv, and moon.
cp .env.example .env
pnpm install
uv sync --project apps/inference
Don’t forget to set VITE_INFERENCE_URL in .env.
Development
pnpm dev
Research Credits
- Questure Tracker
- MiCT-RANet for ASL Fingerspelling
- A Two-Stream Neural Network for Pose-Based Handshape Recognition in American Sign Language
- Mixed 3D/2D Convolutional Tube for Human Action Recognition
- Fingerspelling Recognition in the Wild with Iterative Visual Attention
- FSBoard: Over 3 million characters of ASL fingerspelling collected via smartphones
Similar Articles
Hand Wave
Hand Wave is a smart glasses product that translates sign language into speech, aimed at improving accessibility for deaf and hard-of-hearing users.
Show HN: Subvocal – Talk to your computer without making noise
Show HN: Subvocal (YC F26) presents smart glasses that decode silently mouthed or internal speech into text using RF sensing through the face, replacing their earlier EMG prototype with antenna-embedded frames and foundation models trained on scaled pretraining data.
Google Gemini can now transcribe Sign Language via video
Google Gemini now supports sign language transcription from video, a notable accessibility advancement for AI models.
@GoogleDeepMind: For years, building AI for sign language has been slow due to complex technical challenges and misconceptions about how…
Google DeepMind has developed an AI model that translates sign language by directly converting hand, body, and face movements into text, addressing long-standing technical challenges.
Toward Real-Time Sentence-Level Sign Language Translation
This paper presents a sentence-level sign language translation system fine-tuned with QLoRA on a subset of How2Sign, achieving BLEU 15.9. Its main contribution is a hardware-aware streaming pipeline using a Raspberry Pi 4B client and a CPU/GPU backend, reducing mean latency by 27.71%.