Downloads · 30 days
10
42% of all-time downloads
Skunk0/openglasses-fingerspelling-ctc
openglasses-fingerspelling-ctc is a machine learning model from Skunk0. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for coreml. The card lists the license as apache-2.0.
On-device American Sign Language fingerspelling recognizer used by the OpenGlasses accessibility tier. A CTC sequence model over MediaPipe Holistic landmarks, converted to a fixed-window Core ML program:
Downloads · 30 days
10
42% of all-time downloads
All-time downloads
24
Public
Repo size
32.5 MB
Likes
0
Public
Click a slice to open those files.
.task13.7 MB · 42%
From the Hugging Face model README
On-device American Sign Language fingerspelling recognizer used by the OpenGlasses accessibility tier. A CTC sequence model over MediaPipe Holistic landmarks, converted to a fixed-window Core ML program:
features (1, 768, 1629) float32 — up to 768 frames × 543 landmarks × xyz
(canonical order: face 0–467, left hand 468–488, pose 489–521, right hand 522–542),
per-window standardised, NaN→0, zero-padded — plus mask (1, 768) float32 validity.(1, 384, 62) CTC logits (stride 2; read the first ⌈T/2⌉ rows; class 0 is
the blank, classes 1–59 map through vocab.txt, the last two are auxiliary tokens).| File | Purpose |
|---|---|
Fingerspelling2P.mlpackage | the Core ML model (fp16, iOS 17+) |
vocab.txt | CTC charset sidecar (<blank> + 59 symbols, one per line) |
holistic_landmarker.task | MediaPipe holistic landmark extractor consumed alongside the model |
LICENSE).holistic_landmarker.task is a MediaPipe model asset (Google), Apache-2.0.