proofbird/gector-bert-fr

Proofbird Grammar — French

gector-bert-fr · on-device French grammar correction

Version 1.0.0 · run 2026-11-07-1303 · tag v1.0.0, the files the Proofbird app downloads. Pin it with revision="v1.0.0". Versions: a new training run raises the first number, changed guards or rules the second, card or metadata fixes the third.

A GECToR-style sequence tagger for French grammatical error correction, exported to ONNX (fp32) to run on the CPU. It is the on-device grammar model of Proofbird, a writing assistant for Windows, and it is published here so anyone can inspect what runs on their machine.

GECToR does not rewrite text. For each token it predicts one edit tag (keep, delete, replace with a word, append a word, change case, change an ending), and the edits are applied and the sentence re-tagged up to five times. The tagger only proposes local edits; it never paraphrases.

Quick start

No API key, no GPU. One file, quickstart.py, downloads the model and runs it with ONNX Runtime.

pip install onnxruntime tokenizers huggingface_hub

import importlib.util
from huggingface_hub import hf_hub_download

spec = importlib.util.spec_from_file_location("quickstart", hf_hub_download("proofbird/gector-bert-fr", "quickstart.py"))
quickstart = importlib.util.module_from_spec(spec)
spec.loader.exec_module(quickstart)

model = quickstart.Gector("proofbird/gector-bert-fr")
corrected, suggestions = model.correct("Ma sœur sont très content.")
print(corrected)
print(suggestions)

Ma sœur est très contente.
[{"start": 8, "length": 4, "original": "sont", "replacement": "est"}, {"start": 18, "length": 7, "original": "content", "replacement": "contente"}]

Each suggestion gives the character position in your text (start, length), what is there now (original) and what to put instead (replacement), so you can underline it and offer the fix. From the command line: python quickstart.py "Ma sœur sont très content." prints every step below.

What it corrects

Gender and number agreement (adjectives, past participles after être, nouns after numerals and determiners: Les filles sont fatigué → fatiguées, Les acteurs étaient excellent → excellents), subject-verb agreement (Les enfants joue → jouent), the verb's person after vous and tu (Vous a raison → avez), accents that change the word (a → à, ou → où in questions), contracted prepositions (à le → au, de le → du), elision (le arbre → l'arbre), doubled words and articles (la la porte), common homophones, and capitalisation at the start of a sentence.

How it was trained

• Base encoder: Geotrend/bert-base-fr-cased (Apache-2.0), the French reduction of multilingual BERT. A tagging head (5 000 edit labels) and an error-detection head sit on top.
• Data: synthetic only. 3 000 000 sentences from French Wikipedia (wikimedia/wikipedia, 20231101.fr) and 250 000 sentences from Tatoeba were corrupted by hand-written French error rules; about 10% stay clean, so the model learns to leave correct text alone. 176 000 additional template sentences teach patterns Wikipedia rarely contains (first and second person, questions, plural participles, agreement in a later clause).
• No learner corpora and no non-commercial data of any kind. No user text was used.
• One epoch (111 854 steps, batch 64, learning rate 3e-5) on one NVIDIA L4. Run id 2026-11-07-1303.

How it was measured

Check	Result
Gold set (618 hand-written sentences: 478 with one error each, 140 correct)	472 fixed, 140 left alone, 6 missed, 0 made worse
False alarms on 4 000 everyday Tatoeba sentences (held out from training)	17 changed (0.43%); 9 of them correct an error in Tatoeba's own text
Stability: the gold re-run with one extra token in front of each sentence	4 sentences change result (the 4 capitalisation rows change by construction and are not counted)

The gold score is with the apply-side guards in gector-guards.json (below). The model was trained for precision: a missed error costs less than a wrong correction. The Tatoeba changes include real fixes of Tatoeba's text (le vie → la vie, Il est allé a Tokyo → à, l'hotel → l'hôtel) and eight false alarms, for example un jour ou l'autre → où and an object pronoun changed (Nous ne la comprîmes pas → le). Known misses: où at the end of a sentence or after a comma clause, and an irregular feminine in a later clause (la voiture était très vieux). Without the guards the raw model can propose a non-word for an irregular adjective (vieux → vieuse); the Proofbird app holds every non-word back. It has not been measured on learner essays.

Files

File	What it is
model.onnx	The tagger (fp32, opset 17). Inputs input_ids, attention_mask; outputs logits_labels [1, T, 5000] and logits_d [1, T, 2].
config.json	The edit-label vocabulary (id2label).
vocab.txt, tokenizer.json, tokenizer_config.json	The base encoder's WordPiece tokenizer.
gector-meta.json	Export facts: encoder, tokenizer family, decoding defaults, run id, version.
gector-guards.json	Apply-side guards: rules that hold back an edit the model gets wrong in a known way (for example la → le after a past participle, where la is the adverb là). Part of the measured result.
language-rules.json	Language facts the runtime needs (sentence-final punctuation handling).
verb-form-vocab.txt	Empty for French: verb forms are fixed by ending changes and whole-word edits.
grammar-messages.json	Short explanations shown with each correction.
quickstart.py	A complete Python runner: download, tokenize, run, decode, apply, suggestions. See Quick start.
quickstart.ipynb	The same, as a notebook (the Open in Colab button).

The Proofbird app runs the same algorithm in C# with ONNX Runtime; the files are standard, so any GECToR-style decoder can use them.

How it works, step by step

The model never sees letters and never writes text. It reads numbers (token ids) and answers, for every word, which edit to make: one of 5 000 tags such as $KEEP, $DELETE, $APPEND_et, $REPLACE_as or $TRANSFORM_SUF__e (change a word's ending). quickstart.py does everything around it. This is the real run of the example above.

1. Prepare the text. language-rules.json says the final full stop comes off before the model sees the sentence (it goes back on at the end): Ma sœur sont très content.

2. The request. The words are looked up in the model's dictionary (vocab.txt). A rare word is split into pieces; the edit is read at its first piece. [CLS] stands for a dummy first word, $START, so an edit on it can add a word at the very beginning; [SEP] marks the end.

words           $START  Ma  sœur  sont  très  content
tokens          [CLS] Ma sœur sont très content [SEP]
input_ids       [11, 2191, 10685, 583, 1800, 4552, 12]
attention_mask  [1, 1, 1, 1, 1, 1, 1]

Two inputs, both whole numbers (int64), shape [1, 7]: one sentence of 7 tokens.

3. The response. Two outputs (float32): logits_labels [1, 7, 5000], a score for each of the 5 000 edits at every token, and logits_d [1, 7, 2], a score for "this word is correct" and "this word is wrong". A softmax turns each row into probabilities; the most probable edit at each word's first token is the one applied.

4. Pass by pass. The corrected sentence goes back in, until a pass changes nothing (at most five passes). Connected errors are fixed one after the other.

Pass 1: Ma sœur sont très content

Word	Wrong	Chosen edit	Probability
$START	0.0%	$KEEP	100.0%
Ma	0.0%	$KEEP	100.0%
sœur	0.0%	$KEEP	100.0%
sont	99.8%	$REPLACE_est	99.9%
très	0.0%	$KEEP	100.0%
content	1.8%	$KEEP	98.3%

→ Ma sœur est très content

Pass 2: Ma sœur est très content

Word	Wrong	Chosen edit	Probability
$START	0.0%	$KEEP	100.0%
Ma	0.0%	$KEEP	100.0%
sœur	0.0%	$KEEP	100.0%
est	0.0%	$KEEP	100.0%
très	0.0%	$KEEP	100.0%
content	99.7%	$TRANSFORM_SUF__e	99.9%

→ Ma sœur est très contente

Pass 3: Ma sœur est très contente

Word	Wrong	Chosen edit	Probability
$START	0.0%	$KEEP	100.0%
Ma	0.0%	$KEEP	100.0%
sœur	0.0%	$KEEP	100.0%
est	0.0%	$KEEP	100.0%
très	0.0%	$KEEP	100.0%
contente	0.0%	$KEEP	100.0%

→ Ma sœur est très contente — no change, so it stops.

5. The suggestions. The original and the final words are compared, and each changed stretch becomes one suggestion with its position in the original text (unchanged text keeps its own spacing), as in the Quick start output above.

6. Settings. Gector(repo, keep_confidence=0.0, min_error_prob=0.0) takes the two GECToR precision knobs (the Proofbird app runs with both at 0, and at most five passes):

• keep_confidence adds a bonus to $KEEP before choosing: higher means fewer, safer edits.
• min_error_prob ignores an edit the model is less sure of, and leaves the whole sentence alone when no word is at least that likely to be wrong. With min_error_prob=0.9 the example is still corrected (Ma sœur est très contente.): the model is 99.8% sure one word is wrong.

What Proofbird adds

quickstart.py is the model on its own. The Proofbird app runs the same algorithm in C# and adds:

• Guards (gector-guards.json, in this repository): per-language rules that hold back edits we measured as wrong in a known shape. The scores under How it was measured are with the guards.
• Spelling, checked separately by the operating system's spell checker; the guards use it so a grammar edit is not made on a word that is misspelled.
• A card for each change that names the error ("Subject–verb agreement") and, on request, explains it.

Licence and attribution

The model weights and the files in this repository are released under the Apache License 2.0. If you redistribute the model or a model built from it, keep the NOTICE file with it (Apache-2.0, section 4(d)).

The training data carries its own terms. Wikipedia text is © Wikipedia contributors, CC BY-SA 4.0. Tatoeba sentences are from tatoeba.org, CC BY 2.0 FR. The base encoder is Geotrend/bert-base-fr-cased by Geotrend (Abdaoui et al., 2020, Load What You Need: Smaller Versions of Multilingual BERT), Apache-2.0. The tagging scheme follows GECToR (Omelianchuk et al., 2020, GECToR – Grammatical Error Correction: Tag, Not Rewrite).

How to cite

If you use or build on this model, please cite it:

@misc{hartnett2026gectorfr,
  author       = {Hartnett, Patrick Andrew},
  title        = {Proofbird GECToR grammar model (French)},
  year         = {2026},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/proofbird/gector-bert-fr}},
  note         = {Proofbird, https://proofbird.app}
}

If you build on this model, a link back to this page is appreciated.

Contact

Published by Patrick Andrew Hartnett as personal work. Questions and reports: open a discussion on this repository.