Mindket

Try Proofbird Grammar

Newversion 1 · updated

Overview

Check the grammar of a sentence in English, Italian, Spanish, French or German with Proofbird's models running inside your browser. Your text stays on your computer.

Try Proofbird Grammar is a kit in the Writing category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.

At a glance

You need
  • Python and pip, for the hf download command
  • A web browser
  • About 450 MB of browser storage for each language you try
Runs in
  • A web browser, on the Space's page at Hugging Face
  • A web browser on Windows, macOS or Linux, from a local copy of the files
Start with
pip install -U huggingface_hub
hf download proofbird/try-grammar --repo-type space --local-dir try-grammar
cd try-grammar

Platform

WindowsOperating system
macOSOperating system
LinuxOperating system

About

What it is

This page runs Proofbird's grammar models inside your web browser. It checks a sentence in English, Italian, Spanish, French or German and suggests corrections.

The model for your language downloads once, at about 450 MB, and your browser keeps it. After that, the checking happens on your own computer, so the text you type stays there.

Who it suits

It suits writers, students and language learners who want a quick grammar check without sending text to a server. Developers can read how a grammar model runs in plain JavaScript.

IndustryWho uses itHow they use itExample
EducationLanguage learnersType a practice sentence and read the suggested fixChecking a Spanish or German homework sentence
PublishingEditors and writersTest a sentence for grammar slipsChecking a line of English copy before sending it
Privacy-minded workAnyone with sensitive textCheck a sentence without it leaving the computerTesting wording from a private draft
AI developmentDevelopersRead gector.js and app.js to see how the model is run in a browserStudying an on-device grammar model

Skip it if you want explanations for each change or a spell checker, since this page is the model on its own.

Where to use it

The page runs in these places.

  • A web browser, on the Space's page at Hugging Face
  • A web browser on Windows, macOS or Linux, from a local copy of the files
Use caseWhoWhat they get back
Check one sentenceWriters and studentsCorrections and suggestions for that sentence
Try a model in a new languageLanguage learnersThe same check in a second language
Study the browser portDevelopersA JavaScript file that mirrors the Python quickstart

How to set it up

Online you need only a browser and some disk room for the model. A local copy needs these.

  • Python and pip, for the hf download command
  • A web browser
  • About 450 MB of browser storage for each language you try
  1. Install the huggingface_hub package.
  2. Download the Space's files into a folder with the hf command.
  3. Move into that folder.
  4. Open index.html in a web browser.
pip install -U huggingface_hub
hf download proofbird/try-grammar --repo-type space --local-dir try-grammar
cd try-grammar

How to use it

Open the Space's page, or index.html in your local copy, and choose the language you want. The model downloads the first time. Then type one sentence and read what it suggests. The page checks one sentence at a time.

Example

You open the page for English and wait for the model to download. You type a sentence with a mistake in it. The page returns a corrected version of the sentence and the suggestions behind it.

For newcomers and experts

If you are new, open the Space's page, wait for the first download and try a short sentence with one obvious mistake. The next visit is quicker because the browser keeps the model.

If you know the field, gector.js re-implements the quickstart.py of each model in JavaScript and runs the model through ONNX Runtime Web. The author compared it with the Python file on 2,549 gold sentences across the five models and reports identical token ids, corrections and suggestions. The trade-off is a large first download in exchange for no server.

  1. Open the page and pick a language
  2. The browser downloads the model once
  3. You type a sentence
  4. The model runs locally and suggests fixes

Good to know

This is the model alone. Compared with the full Proofbird app, the page lacks the guard rules, the spell checker and the per-change explanations.

  • License: the page's own code is Apache-2.0. Four of the five models are Apache-2.0 and the Spanish one is CC BY 4.0
  • Cost to run: none named
  • Data it reaches: the model files that download into your browser. The text you type stays on your computer
  • Not for: checking a whole document at once, since it checks one sentence at a time

README and files

README

Try Proofbird Grammar

Check the grammar of a sentence in English, Italian, Spanish, French or German with Proofbird's models running inside your browser. Your text stays on your computer.

Made by proofbird on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This page runs Proofbird's grammar models inside your web browser. It checks a sentence in English, Italian, Spanish, French or German and suggests corrections.

The model for your language downloads once, at about 450 MB, and your browser keeps it. After that, the checking happens on your own computer, so the text you type stays there.

Who it suits: It suits writers, students and language learners who want a quick grammar check without sending text to a server. Developers can read how a grammar model runs in plain JavaScript.

Industry | Who uses it | How they use it | Example
Education | Language learners | Type a practice sentence and read the suggested fix | Checking a Spanish or German homework sentence
Publishing | Editors and writers | Test a sentence for grammar slips | Checking a line of English copy before sending it
Privacy-minded work | Anyone with sensitive text | Check a sentence without it leaving the computer | Testing wording from a private draft
AI development | Developers | Read gector.js and app.js to see how the model is run in a browser | Studying an on-device grammar model

Skip it if you want explanations for each change or a spell checker, since this page is the model on its own.

Where to use it: The page runs in these places.

  • A web browser, on the Space's page at Hugging Face
  • A web browser on Windows, macOS or Linux, from a local copy of the files
Use case | Who | What they get back
Check one sentence | Writers and students | Corrections and suggestions for that sentence
Try a model in a new language | Language learners | The same check in a second language
Study the browser port | Developers | A JavaScript file that mirrors the Python quickstart

How to set it up: Online you need only a browser and some disk room for the model. A local copy needs these.

  • Python and pip, for the hf download command
  • A web browser
  • About 450 MB of browser storage for each language you try
  1. Install the huggingface_hub package.
  2. Download the Space's files into a folder with the hf command.
  3. Move into that folder.
  4. Open index.html in a web browser.
pip install -U huggingface_hub
hf download proofbird/try-grammar --repo-type space --local-dir try-grammar
cd try-grammar

How to use it: Open the Space's page, or index.html in your local copy, and choose the language you want. The model downloads the first time. Then type one sentence and read what it suggests. The page checks one sentence at a time.

Example: You open the page for English and wait for the model to download. You type a sentence with a mistake in it. The page returns a corrected version of the sentence and the suggestions behind it.

For newcomers and experts: If you are new, open the Space's page, wait for the first download and try a short sentence with one obvious mistake. The next visit is quicker because the browser keeps the model.

If you know the field, gector.js re-implements the quickstart.py of each model in JavaScript and runs the model through ONNX Runtime Web. The author compared it with the Python file on 2,549 gold sentences across the five models and reports identical token ids, corrections and suggestions. The trade-off is a large first download in exchange for no server.

Open the page and pick a language
The browser downloads the model once
You type a sentence
The model runs locally and suggests fixes

Good to know: This is the model alone. Compared with the full Proofbird app, the page lacks the guard rules, the spell checker and the per-change explanations.

  • License: the page's own code is Apache-2.0. Four of the five models are Apache-2.0 and the Spanish one is CC BY 4.0
  • Cost to run: none named
  • Data it reaches: the model files that download into your browser. The text you type stays on your computer
  • Not for: checking a whole document at once, since it checks one sentence at a time

On Hugging Face, 13 November 2026

  • Likes: 1
  • Built with: static
  • License: apache-2.0

Links

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.

Files
README.md  5 KB

1 file, 5 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-12

Compare with similar

Listed Hugging Face Spaces in the same category that share the most tags with this one.

ProductLikesBuilt withLicenseLast change
Try Proofbird Grammar This page1staticapache-2.0
AI Text HumanizerShares static232staticmit
Ai Journalism SkillsShares static20staticcc-by-4.0
Numbers as Mindket last read them, on 2026-11-12.

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

anaksor-ocr

Sokheng · Kit

Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…

New

Qwen2.5-7B-Instruct as GGUF files in eight quantization sizes, to chat with locally through llama.cpp. For people who want a capable 7.6B model on their own co…

New

ACE-Step 1.5 XL SFT

ACE-Step · Kit

Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…

New

Similar in Writing

See all in Writing

Rewrites English text with fewer grammar mistakes, using a T5 model trained on the JFLEG dataset. Made by vennify for writers, students and developers who want…

New

Translates between 33 languages on your own device with a 1.8B model squeezed to 1.25 bits, about 440 MB as GGUF files for llama.cpp. For developers adding off…

New

Summarizes, answers questions about and continues book-length text with a fine-tuned 27B model that uses Gated DeltaNet layers, in English and Japanese. For pe…

New