Automatic voice-synthetised summaries of latest research papers on arXiv

Overview

PaperWhisperer

PaperWhisperer is a Python application that keeps you up-to-date with research papers. How? It retrieves the latest articles from arXiv on a topic, by performing a keyword-based search. Then, it creates vocal summaries of the articles using Text-To-Speech and stores them to disk.

Installation

To install the package, move to the root of the repo and type in the console:

$ pip install .

If you plan to develop the package further, install the package in editable mode also installing the packages necessary to run unittests:

$ pip install -e .[test]

Testing

To run unittests, issue the following command from the root of the repo:

$ pytest

Package structure

The package is divided into 2 sub-packages:

  • retrieval
  • tts

retrieval contains data structures and facilities necessary to retrieve articles from arXiv. Under the hood, the app uses arxiv, a Python package that is a wrapper around the arXiv free API.

tts has facilities to generate speech renditions of text-based article summaries. The summary of an article consists of its title, authors, and abstract. Speech synthesis is performed using Google Cloud Text-To-Speech.

Setting up Google Cloud Text-To-Speech

PaperWhisperer uses Google Cloud Text-To-Speech to synthesise speech.

In order to be able to use this service, you should:

  1. create an account on Google Cloud,
  2. create a Cloud Platform project,
  3. enable the Text-To-Speech API in the project
  4. setup authentication
  5. download a Json private key

More info on how to set up Google Cloud Text-To-Speech

Environment variables

The app uses an environment variable called GOOGLE_APPLICATION_CREDENTIALS to connect to Google Cloud Text-To-Speech safely.

In config.yml, set GOOGLE_APPLICATION_CREDENTIALS to the path of the Json private key you previously downloaded while setting up the Google service.

Without this step, you won't be able to connect to Google Cloud Text-To-Speech, and the app will throw an error.

How to create summaries

To create summaries for a keyword search, use the create_summaries entry point. This is the only console script of the package and the main entry point of the application.

Below is an example of how you can run the script:

$ create_summaries "generate chord progressions" 100 /save/dir 40

The script takes 4 positional arguments:

  • keywords used for searching articles (more than one keyword is possible)
  • maximum number of articles to retrieve
  • directory where to store vocal summaries
  • retrieve articles no older than this integer value in days

Dependencies

PaperWhisperer depends on the following packages:

  • arxiv==1.2.0
  • google-cloud-texttospeech
  • python-dotenv

YouTube video

Learn more about PaperWhisperer in this project presentation video on The Sound of AI YouTube channel.

Owner
Valerio Velardo
AI audio/music researcher. Love Python.
Valerio Velardo
Checkout some cool self-projects you can try your hands on to curb your boredom this December!

SoC-Winter Checkout some cool self-projects you can try your hands on to curb your boredom this December! These are short projects that you can do you

Web and Coding Club, IIT Bombay 29 Nov 08, 2022
PuppetGAN - Cross-Domain Feature Disentanglement and Manipulation just got way better! 🚀

Better Cross-Domain Feature Disentanglement and Manipulation with Improved PuppetGAN Quite cool... Right? Introduction This repo contains a TensorFlow

Giorgos Karantonis 5 Aug 25, 2022
A modified version of DeepMind's Alphafold2 to divide CPU part (MSA and template searching) and GPU part (prediction model)

ParallelFold Author: Bozitao Zhong This is a modified version of DeepMind's Alphafold2 to divide CPU part (MSA and template searching) and GPU part (p

Bozitao Zhong 77 Dec 22, 2022
A clean and extensible PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

A clean and extensible PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners A PyTorch re-implementation of Mask Autoencoder trai

Tianyu Hua 23 Dec 13, 2022
Hybrid Neural Fusion for Full-frame Video Stabilization

FuSta: Hybrid Neural Fusion for Full-frame Video Stabilization Project Page | Video | Paper | Google Colab Setup Setup environment for [Yu and Ramamoo

Yu-Lun Liu 430 Jan 04, 2023
Cognate Detection Repository

Cognate Detection Repository Details This repository contains the data for two publications: Challenge Dataset of Cognates and False Friend Pairs from

Diptesh Kanojia 1 Apr 26, 2022
Balancing Principle for Unsupervised Domain Adaptation

Blancing Principle for Domain Adaptation NeurIPS 2021 Paper Abstract We address the unsolved algorithm design problem of choosing a justified regulari

Marius-Constantin Dinu 4 Dec 15, 2022
Code for Understanding Pooling in Graph Neural Networks

Select, Reduce, Connect This repository contains the code used for the experiments of: "Understanding Pooling in Graph Neural Networks" Setup Install

Daniele Grattarola 37 Dec 13, 2022
Compute execution plan: A DAG representation of work that you want to get done. Individual nodes of the DAG could be simple python or shell tasks or complex deeply nested parallel branches or embedded DAGs themselves.

Hello from magnus Magnus provides four capabilities for data teams: Compute execution plan: A DAG representation of work that you want to get done. In

12 Feb 08, 2022
Diverse Branch Block: Building a Convolution as an Inception-like Unit

Diverse Branch Block: Building a Convolution as an Inception-like Unit (PyTorch) (CVPR-2021) DBB is a powerful ConvNet building block to replace regul

253 Dec 24, 2022
'Solving the sampling problem of the Sycamore quantum supremacy circuits

solve_sycamore This repo contains data, contraction code, and contraction order for the paper ''Solving the sampling problem of the Sycamore quantum s

Feng Pan 29 Nov 28, 2022
A rough implementation of the paper "A Steering Algorithm for Redirected Walking Using Reinforcement Learning"

A rough implementation of the paper "A Steering Algorithm for Redirected Walking Using Reinforcement Learning"

Somnus ï½€Chen 2 Jun 09, 2022
Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020

XDVioDet Official implementation of "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision" ECCV2020. The proj

peng 64 Dec 12, 2022
TensorFlow 2 implementation of the Yahoo Open-NSFW model

TensorFlow 2 implementation of the Yahoo Open-NSFW model

Bosco Yung 101 Jan 01, 2023
A learning-based data collection tool for human segmentation

FullBodyFilter A Learning-Based Data Collection Tool For Human Segmentation Contents Documentation Source Code and Scripts Overview of Project Usage O

Robert Jiang 4 Jun 24, 2022
Emotion classification of online comments based on RNN

emotion_classification Emotion classification of online comments based on RNN, the accuracy of the model in the test set reaches 99% data: Large Movie

1 Nov 23, 2021
Weighted QMIX: Expanding Monotonic Value Function Factorisation

This repo contains the cleaned-up code that was used in "Weighted QMIX: Expanding Monotonic Value Function Factorisation"

whirl 82 Dec 29, 2022
TensorFlow Metal Backend on Apple Silicon Experiments (just for fun)

tf-metal-experiments TensorFlow Metal Backend on Apple Silicon Experiments (just for fun) Setup This is tested on M1 series Apple Silicon SOC only. Te

Timothy Liu 161 Jan 03, 2023
Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

PSML paper: Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors PSML_IONE,PSML_ABNE,PSML_DEEPLINK,PSML_SNNA: numpy

13 Nov 27, 2022
RSC-Net: 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos

RSC-Net: 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos Implementation for "3D Human Pose, Shape and Texture from Low-Resoluti

XiangyuXu 42 Nov 10, 2022