|
--- |
|
language: "en" |
|
tags: |
|
- grammar |
|
- text-generation |
|
license: "CC BY-NC-SA 4.0" |
|
datasets: |
|
- jfleg |
|
|
|
--- |
|
|
|
# T5 Grammar Correction |
|
|
|
This model generates a revised version of inputted text with the goal of containing fewer grammatical errors. |
|
It was trained with [Happy Transformer](https://github.com/EricFillion/happy-transformer) |
|
using a dataset called [JFLEG](https://arxiv.org/abs/1702.04066). |
|
|
|
## Usage |
|
|
|
`pip install happytransformer ` |
|
|
|
```python |
|
from happytransformer import HappyTextToText |
|
|
|
happy_tt = HappyTextToText("T5", "vennify/t5-base-grammar-correction") |
|
|
|
args = TTSettings(num_beams=5, min_length=1) |
|
|
|
result = happy_tt.generate_text("This sentences has has bads grammar.", args=args) |
|
|
|
print(result.text) # This sentence has bad grammar. |
|
|
|
|
|
``` |