📝An easy-to-use package to restore punctuation of the text.

Related tags

Text Data & NLPrpunct
Overview

✏️ rpunct - Restore Punctuation

forthebadge

This repo contains code for Punctuation restoration.

This package is intended for direct use as a punctuation restoration model for the general English language. Alternatively, you can use this for further fine-tuning on domain-specific texts for punctuation restoration tasks. It uses HuggingFace's bert-base-uncased model weights that have been fine-tuned for Punctuation restoration.

Punctuation restoration works on arbitrarily large text. And uses GPU if it's available otherwise will default to CPU.

List of punctuations we restore:

  • Upper-casing
  • Period: .
  • Exclamation: !
  • Question Mark: ?
  • Comma: ,
  • Colon: :
  • Semi-colon: ;
  • Apostrophe: '
  • Dash: -

🚀 Usage

Below is a quick way to get up and running with the model.

  1. First, install the package.
pip install rpunct
  1. Sample python code.
from rpunct import RestorePuncts
# The default language is 'english'
rpunct = RestorePuncts()
rpunct.punctuate("""in 2018 cornell researchers built a high-powered detector that in combination with an algorithm-driven process called ptychography set a world record
by tripling the resolution of a state-of-the-art electron microscope as successful as it was that approach had a weakness it only worked with ultrathin samples that were
a few atoms thick anything thicker would cause the electrons to scatter in ways that could not be disentangled now a team again led by david muller the samuel b eckert
professor of engineering has bested its own record by a factor of two with an electron microscope pixel array detector empad that incorporates even more sophisticated
3d reconstruction algorithms the resolution is so fine-tuned the only blurring that remains is the thermal jiggling of the atoms themselves""")
# Outputs the following:
# In 2018, Cornell researchers built a high-powered detector that, in combination with an algorithm-driven process called Ptychography, set a world record by tripling the
# resolution of a state-of-the-art electron microscope. As successful as it was, that approach had a weakness. It only worked with ultrathin samples that were a few atoms
# thick. Anything thicker would cause the electrons to scatter in ways that could not be disentangled. Now, a team again led by David Muller, the Samuel B. 
# Eckert Professor of Engineering, has bested its own record by a factor of two with an Electron microscope pixel array detector empad that incorporates even more
# sophisticated 3d reconstruction algorithms. The resolution is so fine-tuned the only blurring that remains is the thermal jiggling of the atoms themselves.

🎯 Accuracy

Here is the number of product reviews we used for finetuning the model:

Language Number of text samples
English 560,000

We found the best convergence around 3 epochs, which is what presented here and available via a download.


The fine-tuned model obtained the following accuracy on 45,990 held-out text samples:

Accuracy Overall F1 Eval Support
91% 90% 45,990

💻 🎯 Further Fine-Tuning

To start fine-tuning or training please look into training/train.py file. Running python training/train.py will replicate the results of this model.


Contact

Contact Daulet Nurmanbetov for questions, feedback and/or requests for similar models.


Comments
  • Update requirements.txt

    Update requirements.txt

    ERROR: Could not find a version that satisfies the requirement torch==1.8.1 (from rpunct) (from versions: 1.11.0, 1.12.0, 1.12.1, 1.13.0) ERROR: No matching distribution found for torch==1.8.1

    opened by Rukaya-lab 0
  • Forked repo with fixes

    Forked repo with fixes

    I forked this repository (link here) to fix the outdated dependencies and incompatibility with non-CUDA machines. If anyone needs these fixes, feel free to install from the fork:

    pip install git+https://github.com/samwaterbury/rpunct.git
    

    Hopefully this repository is updated or another maintainer is assigned. And thanks to the creator @Felflare, this is a useful tool!

    opened by samwaterbury 2
  • Requirements shouldn't ask for such specific versions

    Requirements shouldn't ask for such specific versions

    First, thanks a lot for providing this package :)

    Currently, the requirements.txt, and thus the dependencies in the setup.py are for very specific versions of Pytorch etc. This shouldn't be the case if you want this package to be used as a general library (think of a second package that would do the same but ask for an incompatible version of PyTorch and would prevent any possible installation of the two together). The end user might also be needing a more recent version of PyTorch. Given that PyTorch is almost always backward compatible, and quite stable, I think the requirements for it could be changed from ==1.8.1 to >=1.8.1. I believe the same would be true for the other packages.

    opened by adefossez 2
  • Added ability to pass additional parameters to simpletransformer ner in RestorePuncts class.

    Added ability to pass additional parameters to simpletransformer ner in RestorePuncts class.

    Thanks for the great library! When running this without a GPU I had problems. I think there is a simple fix. The simple transformer NER model defaults to enabling cuda. This PR allows the user to pass a dictionary of arguments specifically for the simpletransformers NER model. So you can now run the code on a CPU by initializing rpunct like so

    rpunct = RestorePuncts(ner_args={"use_cuda": False})
    

    Before this change, when running rpunct examples on the CPU the following error occurs:

    from rpunct import RestorePuncts
    # The default language is 'english'
    rpunct = RestorePuncts()
    rpunct.punctuate("""in 2018 cornell researchers built a high-powered detector that in combination with an algorithm-driven process called ptychography set a world record
    by tripling the resolution of a state-of-the-art electron microscope as successful as it was that approach had a weakness it only worked with ultrathin samples that were
    a few atoms thick anything thicker would cause the electrons to scatter in ways that could not be disentangled now a team again led by david muller the samuel b eckert
    professor of engineering has bested its own record by a factor of two with an electron microscope pixel array detector empad that incorporates even more sophisticated
    3d reconstruction algorithms the resolution is so fine-tuned the only blurring that remains is the thermal jiggling of the atoms themselves""")
    
    

    ValueError Traceback (most recent call last) /var/folders/hx/dhzhl_x51118fm5cd13vzh2h0000gn/T/ipykernel_10548/194907560.py in 1 from rpunct import RestorePuncts 2 # The default language is 'english' ----> 3 rpunct = RestorePuncts() 4 rpunct.punctuate("""in 2018 cornell researchers built a high-powered detector that in combination with an algorithm-driven process called ptychography set a world record 5 by tripling the resolution of a state-of-the-art electron microscope as successful as it was that approach had a weakness it only worked with ultrathin samples that were

    ~/repos/rpunct/rpunct/punctuate.py in init(self, wrds_per_pred, ner_args) 19 if ner_args is None: 20 ner_args = {} ---> 21 self.model = NERModel("bert", "felflare/bert-restore-punctuation", labels=self.valid_labels, 22 args={"silent": True, "max_seq_length": 512}, **ner_args) 23

    ~/repos/transformers/transformer-env/lib/python3.8/site-packages/simpletransformers/ner/ner_model.py in init(self, model_type, model_name, labels, args, use_cuda, cuda_device, onnx_execution_provider, **kwargs) 209 self.device = torch.device(f"cuda:{cuda_device}") 210 else: --> 211 raise ValueError( 212 "'use_cuda' set to True when cuda is unavailable." 213 "Make sure CUDA is available or set use_cuda=False."

    ValueError: 'use_cuda' set to True when cuda is unavailable.Make sure CUDA is available or set use_cuda=False.

    opened by nbertagnolli 1
  • add use_cuda parameter

    add use_cuda parameter

    using the package in an environment without cuda support causes it to fail. Adding the parameter to shut it off if necessary allows it to function normall.

    opened by mjfox3 1
Releases(1.0.1)
Owner
Daulet Nurmanbetov
Deep Learning, AI and Finance
Daulet Nurmanbetov
An ultra fast tiny model for lane detection, using onnx_parser, TensorRTAPI, torch2trt to accelerate. our model support for int8, dynamic input and profiling. (Nvidia-Alibaba-TensoRT-hackathon2021)

Ultra_Fast_Lane_Detection_TensorRT An ultra fast tiny model for lane detection, using onnx_parser, TensorRTAPI to accelerate. our model support for in

steven.yan 121 Dec 27, 2022
ChainKnowledgeGraph, 产业链知识图谱包括A股上市公司、行业和产品共3类实体

ChainKnowledgeGraph, 产业链知识图谱包括A股上市公司、行业和产品共3类实体,包括上市公司所属行业关系、行业上级关系、产品上游原材料关系、产品下游产品关系、公司主营产品、产品小类共6大类。 上市公司4,654家,行业511个,产品95,559条、上游材料56,824条,上级行业480条,下游产品390条,产品小类52,937条,所属行业3,946条。

liuhuanyong 415 Jan 06, 2023
Outreachy TFX custom component project

Schema Curation Custom Component Outreachy TFX custom component project This repo contains the code for Schema Curation Custom Component made as a par

Robert Crowe 5 Jul 16, 2021
Predicting the usefulness of reviews given the review text and metadata surrounding the reviews.

Predicting Yelp Review Quality Table of Contents Introduction Motivation Goal and Central Questions The Data Data Storage and ETL EDA Data Pipeline Da

Jeff Johannsen 3 Nov 27, 2022
BERT Attention Analysis

BERT Attention Analysis This repository contains code for What Does BERT Look At? An Analysis of BERT's Attention. It includes code for getting attent

Kevin Clark 401 Dec 11, 2022
An easy-to-use Python module that helps you to extract the BERT embeddings for a large text dataset (Bengali/English) efficiently.

An easy-to-use Python module that helps you to extract the BERT embeddings for a large text dataset (Bengali/English) efficiently.

Khalid Saifullah 37 Sep 05, 2022
A complete NLP guideline for enthusiasts

NLP-NINJA A complete guide for Natural Language Processing in Python Table of Contents S.No. Topic Level Meaning 1 Tokenization 🤍 Beginner 2 Stemming

MAINAK CHAUDHURI 22 Dec 27, 2022
A python project made to generate code using either OpenAI's codex or GPT-J (Although not as good as codex)

CodeJ A python project made to generate code using either OpenAI's codex or GPT-J (Although not as good as codex) Install requirements pip install -r

TheProtagonist 1 Dec 06, 2021
Sinkhorn Transformer - Practical implementation of Sparse Sinkhorn Attention

Sinkhorn Transformer This is a reproduction of the work outlined in Sparse Sinkhorn Attention, with additional enhancements. It includes a parameteriz

Phil Wang 217 Nov 25, 2022
Search Git commits in natural language

NaLCoS - NAtural Language COmmit Search Search commit messages in your repository in natural language. NaLCoS (NAtural Language COmmit Search) is a co

Pushkar Patel 50 Mar 22, 2022
Simple Python script to scrape youtube channles of "Parity Technologies and Web3 Foundation" and translate them to well-known braille language or any language

Simple Python script to scrape youtube channles of "Parity Technologies and Web3 Foundation" and translate them to well-known braille language or any

Little Endian 1 Apr 28, 2022
Blender addon - Scrub timeline from viewport with a shortcut

Viewport scrub timeline Move in the timeline directly in viewport and snap to nearest keyframe Note : This standalone feature will be added in the nat

Samuel Bernou 40 Nov 07, 2022
Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents [Project Page] [Paper] [Video] Wenlong Huang1, Pieter Abbee

Wenlong Huang 114 Dec 29, 2022
SAVI2I: Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors

SAVI2I: Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors [Paper] [Project Website] Pytorch implementation for SAVI2I. We

Qi Mao 44 Dec 30, 2022
Calibre recipe to convert latest issue of Analyse & Kritik into an ebook

Calibre Recipe für "Analyse & Kritik" Dies ist ein "Recipe" für die Konvertierung der aktuellen Ausgabe der Zeitung Analyse & Kritik in ein Ebook. Es

Henning 3 Jan 04, 2022
A very simple framework for state-of-the-art Natural Language Processing (NLP)

A very simple framework for state-of-the-art NLP. Developed by Humboldt University of Berlin and friends. Flair is: A powerful NLP library. Flair allo

flair 12.3k Jan 02, 2023
ASCEND Chinese-English code-switching dataset

ASCEND (A Spontaneous Chinese-English Dataset) introduces a high-quality resource of spontaneous multi-turn conversational dialogue Chinese-English code-switching corpus collected in Hong Kong.

CAiRE 11 Dec 09, 2022
Guide to using pre-trained large language models of source code

Large Models of Source Code I occasionally train and publicly release large neural language models on programs, including PolyCoder. Here, I describe

Vincent Hellendoorn 947 Dec 28, 2022
Unet-TTS: Improving Unseen Speaker and Style Transfer in One-shot Voice Cloning

Unet-TTS: Improving Unseen Speaker and Style Transfer in One-shot Voice Cloning English | 中文 ❗ Now we provide inferencing code and pre-training models

164 Jan 02, 2023