PyHealth
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
Free picture flashcards for speech therapy and articulation practice. Pick a sound like R, S or TH, choose initial, medial or final, and tap through.
HealthTypeScript · SvelteGitHub @teacherdotdevOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
The maker's introduction consists of the line above. Read the repository README for more details. Repository README ↗
Loading the full README.
Read the full README ↗Picture flashcards for speech sound practice. The teacher picks a sound pack (e.g. R) and where the sound falls in the word (initial, medial, final, or any mix), then taps through cards for as long as the session lasts.
src/lib/deck.ts).localStorage) and keeps loaded
pictures (IndexedDB) on the device. Nothing is sent anywhere.r.ts is a speech therapist's hand-picked list. The other packs are generated
by bun run generate-packs (scripts/generate-packs.ts): words from the
Dale-Chall list of words most 4th graders know, placed by sound and position
using the CMU Pronouncing Dictionary, that have an ARASAAC picture, nouns
first, up to 20 per position. The word lists are downloaded into .word-data/
(not committed), along with review.html, which shows every candidate word with
its picture. To hand-edit a generated pack, delete its first line so the script
leaves it alone; each pack lists more words in an // Also: comment.
To add a sound, add it to SOUNDS in the script (or copy r.ts and fill in
words by hand; leave out a position if the sound has no words for it), then:
bun run generate-packs.PACKS in src/lib/packs/index.ts.bun run pictograms to save the new pictures into src/lib/pictograms/.
bun test src fails if any card's picture is missing.Each word needs an ARASAAC pictogram id: search at https://arasaac.org/pictograms/search
and copy the number from the pictogram's page URL. Pictures are bundled with the
app, so practice never waits on ARASAAC. Pressing Start shows a short loading
screen while the pack's pictures load; they are then saved in IndexedDB
(src/lib/image-store.ts), so the next visit loads them from the device.
bun install
# from the workspace root — never run `bun run dev` directly:
./scripts/agent-dev.mjs speech-flashcards --no-pocketbase
bun test src && bun run check && bun run lint && bun run build
App code: Apache-2.0 (see LICENSE.txt). The ARASAAC pictograms in
src/lib/pictograms/ are not covered by that license. The pictographic symbols used are the property
of the Government of Aragón and have been created by Sergio Palao for ARASAAC
(https://arasaac.org), that distributes them under Creative Commons License
BY-NC-SA. The ARASAAC API may only be used by non-commercial applications.