Text Correction wth deep learning
Pre-trained models for punctuation correction (trained on google news, wikipedia and tatoeba) are available at https://drive.google.com/open?id=1Yd8cJaqfQkrJMbRVWIWtuyo4obTDYu-e
Demo of the punctuation model trained on google news corpus is available at http://bpraneeth.com/projects
This repo uses a seq2seq model written by me in keras with tensorflow backend. The multi-purpose seq2seq model can be found at https://github.com/bedapudi6788/txt2txt/
from deepcorrect import DeepCorrect corrector = DeepCorrect('params_path', 'checkpoint_path') corrector.correct('hey') 'Hey!'
pip install deepcorrect
Points to Note:
Max input and output lengths are 200
Segment text into sentences using https://github.com/bedapudi6788/deepsegment and run punctuation correction on each sentence seperately.
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size deepcorrect-1.0.5-py2.py3-none-any.whl (14.6 kB)||File type Wheel||Python version py2.py3||Upload date||Hashes View|
|Filename, size deepcorrect-1.0.5.tar.gz (3.1 kB)||File type Source||Python version None||Upload date||Hashes View|
Hashes for deepcorrect-1.0.5-py2.py3-none-any.whl