---
license: mit
language:
  - en
  - es
  - fr
  - ru
tags:
  - grammar-correction
  - multilingual
  - mt5
datasets:
  - custom
pipeline_tag: text2text-generation
---

# Multilingual Grammar Corrector using mT5-small Demo(I'll upload them in full in 2 weeks)

This is a fine-tuned [`mT5-small`](https://huggingface.co/google/mt5-small) model for **multilingual grammar correction** in English 99%, Spanish 75%, French 70%, and Russian 80%. It was trained on synthetic and human-curated data to correct grammatical mistakes in short sentences.

## ✨ Example

**Input:**  
> She go to school yesterday.

**Output:**  
> She went to school yesterday.

---

## 🧠 Model Details

- **Architecture:** mT5-small
- **Layers:** 8
- **Heads:** 6
- **Languages supported:** English, Spanish, French, Russian
- **Tokenization:** SentencePiece with special tokens `<pad>`, `</s>`, `<unk>`

## 📦 How to Use

```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model = AutoModelForSeq2SeqLM.from_pretrained("your-username/Multilingual-Grammar-Corrector")
tokenizer = AutoTokenizer.from_pretrained("your-username/Multilingual-Grammar-Corrector")

input_text = "She go to school yesterday."
inputs = tokenizer(input_text, return_tensors="pt")

output = model.generate(**inputs, max_new_tokens=64)
corrected = tokenizer.decode(output[0], skip_special_tokens=True)

print(corrected)  # ➜ She went to school yesterday.