|
|
--- |
|
|
title: Czech Grammar Error Correction ByT5 |
|
|
emoji: ✏️ |
|
|
colorFrom: blue |
|
|
colorTo: green |
|
|
sdk: gradio |
|
|
sdk_version: 4.44.0 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
license: cc-by-sa-4.0 |
|
|
models: |
|
|
- ufal/byt5-large-geccc-mate |
|
|
--- |
|
|
|
|
|
# Czech Grammar Error Correction with ByT5 |
|
|
|
|
|
This Space provides an easy-to-use interface for correcting grammatical errors in Czech text using the state-of-the-art **ByT5-large-geccc-mate** model. |
|
|
|
|
|
## Features |
|
|
|
|
|
- 🔧 **Automatic Grammar Correction**: Fix grammatical errors in Czech text |
|
|
- 📋 **Copy to Clipboard**: Easily copy the corrected text |
|
|
- 🚀 **Fast Processing**: Optimized for quick corrections |
|
|
- 💡 **Example Sentences**: Try the model with pre-loaded examples |
|
|
|
|
|
## Model Information |
|
|
|
|
|
This Space uses the [ufal/byt5-large-geccc-mate](https://huggingface.co/ufal/byt5-large-geccc-mate) model, which is specifically trained for Czech Grammar Error Correction (GEC). |
|
|
|
|
|
The model is based on ByT5 architecture and has been fine-tuned on Czech grammatical error correction datasets. |
|
|
|
|
|
## Usage |
|
|
|
|
|
1. Enter your Czech text in the input field |
|
|
2. Click "Correct Text" or press Enter |
|
|
3. The corrected text will appear in the output field |
|
|
4. Use the "Copy to Clipboard" button to copy the result |
|
|
|
|
|
## Links |
|
|
|
|
|
- [Model Card](https://huggingface.co/ufal/byt5-large-geccc-mate) |
|
|
- [GitHub Repository](https://github.com/ufal/tsd2025-gec) |
|
|
- [Research Paper](https://github.com/ufal/tsd2025-gec/blob/main/guide.md) |
|
|
|
|
|
## Citation |
|
|
|
|
|
If you use this model in your research, please cite the original work by the UFAL team. |
