| language: en | |
| tags: | |
| - grammar | |
| - spell | |
| - correction | |
| # Spellcheck Model | |
| ## Installation | |
| 1. Install Python 3.8 or higher and Docker; | |
| 2. Clone the repo; | |
| 3. Create a virtual environment: `python3 -m venv venv`; | |
| 4. Activate the virtual environment: `source venv/bin/activate`; | |
| 5. Install dependencies: `pip install -r requirements.txt`; | |
| # | |
| ## Usage | |
| ### Training | |
| There's a `data` directory with two files: | |
| 1. `eval.csv`: evaluation dataset; | |
| 2. `train.csv`: training dataset; | |
| Both are in the same format: | |
| ```txt | |
| input,target | |
| "grammar: som sentense","some sentence" | |
| "grammar: anoder centence","another sentence" | |
| ... | |
| ``` | |
| You can edit them to use your own dataset. | |
| Now if you want to fine-tune the existing model here, just run the following commands: | |
| ```bash | |
| docker build -t spellcheck_train . | |
| docker run -v $(pwd):/app spellcheck_train | |
| ``` | |
| Also make sure you have docker running on your machine. | |
| ### Testing | |
| If you want to test your model, just run the following command: | |
| ```bash | |
| python test.py | |
| ``` | |