This is a spelling correction application for our thesis
Create conda environment
conda create -n spellingcorrection python=3.7
Use the package manager pip to install requirements.
cd backend
python -m pip install -r requirements.txt
python -m pip install -e .
Download model checkpoint
# download tokenizer
cd autocorrection
mkdir input
mkdir input/luanvan
cd input/luanvan
gdown <link>
cd ../..
# download model
mkdir weights
mkdir weights/history
mkdir weights/model
gdown <link>
cd ../..
# download pretrained tokenization repair
cd tokenization_repair
mkdir data/estimators/
mkdir data/estimators/lm/
cd data/estimators
gdown https://drive.google.com/drive/folders/1zhtQmPTah7qneEHPHuFHuf3qd5R047-W -O / --folder
cd ../lm
gdown https://drive.google.com/drive/folders/1lG3swcUyUPYOf4ziJGfPQboaYtD5SgTM -O / --folder
Run backend server
python app.py
Use postman to send a post request
{
"text": "hôm nay toi dihoc . cjpcsong rất là vui"
}
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.