All Projects → bedapudi6788 → Deepcorrect

bedapudi6788 / Deepcorrect

Licence: gpl-3.0
Text and Punctuation correction with Deep Learning

Programming Languages

python
139335 projects - #7 most used programming language

Labels

Projects that are alternatives of or similar to Deepcorrect

Augmented seq2seq
enhance seq2seq model for open ended dialog generation
Stars: ✭ 29 (-72.38%)
Mutual labels:  seq2seq
English2cypher
A model to transform english into Cypher queries, based off the CLEVR-graph dataset
Stars: ✭ 54 (-48.57%)
Mutual labels:  seq2seq
Pytorch Seq2seq
An open source framework for seq2seq models in PyTorch.
Stars: ✭ 1,297 (+1135.24%)
Mutual labels:  seq2seq
Hip Hop Seq2seq
DeeCamp 2018,AI有嘻哈 自动写歌词
Stars: ✭ 44 (-58.1%)
Mutual labels:  seq2seq
Pointer Networks Experiments
Sorting numbers with pointer networks
Stars: ✭ 53 (-49.52%)
Mutual labels:  seq2seq
Ai Writer data2doc
PyTorch Implementation of NBA game summary generator.
Stars: ✭ 69 (-34.29%)
Mutual labels:  seq2seq
Attention Ocr
A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.
Stars: ✭ 844 (+703.81%)
Mutual labels:  seq2seq
Tacotron Pytorch
A Pytorch Implementation of Tacotron: End-to-end Text-to-speech Deep-Learning Model
Stars: ✭ 104 (-0.95%)
Mutual labels:  seq2seq
Asr
Stars: ✭ 54 (-48.57%)
Mutual labels:  seq2seq
Im2latex
Pytorch implemention of Deep CNN Encoder + LSTM Decoder with Attention for Image to Latex
Stars: ✭ 84 (-20%)
Mutual labels:  seq2seq
Tensorflow Seq2seq Dialogs
Build conversation Seq2Seq models with TensorFlow
Stars: ✭ 43 (-59.05%)
Mutual labels:  seq2seq
Mxnet Seq2seq
Sequence to sequence learning with MXNET
Stars: ✭ 51 (-51.43%)
Mutual labels:  seq2seq
Xmunmt
An implementation of RNNsearch using TensorFlow
Stars: ✭ 69 (-34.29%)
Mutual labels:  seq2seq
Sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
Stars: ✭ 990 (+842.86%)
Mutual labels:  seq2seq
Cakechat
CakeChat: Emotional Generative Dialog System
Stars: ✭ 1,361 (+1196.19%)
Mutual labels:  seq2seq
Keras Question And Answering Web Api
Question answering system developed using seq2seq and memory network model in Keras
Stars: ✭ 21 (-80%)
Mutual labels:  seq2seq
Sequence To Sequence 101
a series of tutorials on sequence to sequence learning, implemented with PyTorch.
Stars: ✭ 62 (-40.95%)
Mutual labels:  seq2seq
Delta
DELTA is a deep learning based natural language and speech processing platform.
Stars: ✭ 1,479 (+1308.57%)
Mutual labels:  seq2seq
Openseq2seq
Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
Stars: ✭ 1,378 (+1212.38%)
Mutual labels:  seq2seq
Tensorflow seq2seq chatbot
Stars: ✭ 81 (-22.86%)
Mutual labels:  seq2seq

As explored in https://medium.com/@praneethbedapudi/deepcorrection-3-spell-correction-and-simple-grammar-correction-d033a52bc11d , the original aim of this repo is to do spell + simple grammar + punctuation correction. But, since I realised that doing spell correction with seq2seq using autogenerated data is a very dumb idea, I didn't provide usable checkpoints for the same.

This repo was originally meant to be experimental and is very inefficient for punctuation restoration/ correction.

@harikodali is working on faster and better punctuation restoration with seq2seq networks at https://github.com/notAI-tech/fastpunct

Beacause of the above reasons, I am archiving this repo.

deepcorrect

Code and checkpoints corresponding to the posts https://medium.com/@praneethbedapudi/deepcorrection-3-spell-correction-and-simple-grammar-correction-d033a52bc11d and https://medium.com/@praneethbedapudi/deepcorrection2-automatic-punctuation-restoration-ac4a837d92d9

Pre-trained models for punctuation correction (trained on google news, wikipedia and tatoeba) are available at https://drive.google.com/open?id=1Yd8cJaqfQkrJMbRVWIWtuyo4obTDYu-e

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/

Usage:

from deepcorrect import DeepCorrect
corrector = DeepCorrect('params_path', 'checkpoint_path')
corrector.correct('hey')
'Hey!'

Installation:

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.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].