notAI-tech / Fastpunct
Licence: mit
Punctuation restoration and spell correction experiments.
Stars: ✭ 121
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Fastpunct
Bertqa Attention On Steroids
BertQA - Attention on Steroids
Stars: ✭ 112 (-7.44%)
Mutual labels: attention
Datasets knowledge embedding
Datasets for Knowledge Graph Completion with textual information about the entities
Stars: ✭ 116 (-4.13%)
Mutual labels: text
Lambda Networks
Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute
Stars: ✭ 1,497 (+1137.19%)
Mutual labels: attention
Nord Sublime Text
An arctic, north-bluish clean and elegant Sublime Text theme.
Stars: ✭ 109 (-9.92%)
Mutual labels: text
Gtext
Emoji and Hyperlink for Unity UGUI Text ,图文混排、超链接、下划线的UGUI解决方案
Stars: ✭ 113 (-6.61%)
Mutual labels: text
Multiturndialogzoo
Multi-turn dialogue baselines written in PyTorch
Stars: ✭ 106 (-12.4%)
Mutual labels: attention
Sightseq
Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (-4.13%)
Mutual labels: attention
Materialtextfield
A different beautiful Floating Edit Text
Stars: ✭ 1,504 (+1142.98%)
Mutual labels: text
Eyo
🦔 CLI for restoring the letter «ё» (yo) in russian texts
Stars: ✭ 119 (-1.65%)
Mutual labels: text
Render
Go package for easily rendering JSON, XML, binary data, and HTML templates responses.
Stars: ✭ 1,562 (+1190.91%)
Mutual labels: text
Nlp Pretrained Model
A collection of Natural language processing pre-trained models.
Stars: ✭ 122 (+0.83%)
Mutual labels: text
Nlp Models Tensorflow
Gathers machine learning and Tensorflow deep learning models for NLP problems, 1.13 < Tensorflow < 2.0
Stars: ✭ 1,603 (+1224.79%)
Mutual labels: attention
fastPunct : Punctuation restoration and spell correction experiments.
Installation:
pip install --upgrade fastpunct
Supported languages:
english
Usage:
As a python module
from fastpunct import FastPunct
# The default language is 'english'
fastpunct = FastPunct()
fastpunct.punct([
"john smiths dog is creating a ruccus",
"ys jagan is the chief minister of andhra pradesh",
"we visted new york last year in may"
])
# ["John Smith's dog is creating a ruccus.",
# 'Ys Jagan is the chief minister of Andhra Pradesh.',
# 'We visted New York last year in May.']
# punctuation correction with optional spell correction (experimental)
fastpunct.punct([
'johns son peter is marring estella in jun',
'kamal hassan is a gud actr'], correct=True)
# ["John's son Peter is marrying Estella in June.",
# 'Kamal Hassan is a good actor.']
As a docker container
# Start the docker container
docker run -it -p8080:8080 -eBATCH_SIZE=4 notaitech/fastpunct:english
# Run prediction
curl -d '{"data": ["i was hungry i ordered a pizza my name is batman"]}' -H "Content-Type: application/json" "http://localhost:8080/sync"
# {"prediction": ["I was hungry, I ordered a pizza, my name is Batman."], "success": true}
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].