Speech To Text

Chimera: Learning Shared Semantic Space for Speech-to-Text Translation

This is a Pytorch implementation for the “Chimera” paper Learning Shared Semantic Space for Speech-to-Text Translation https://arxiv.org/abs/2105.03095 (accepted by ACL Findings 2021), which aims to bridge the modality gap by unifying the task of MT (textual Machine Translation) and ST (Speech-to-Text Translation). It has achieved new SOTA performance on all 8 language pairs in MuST-C benchmark, by utilizing an external MT corpus. ![](https://github.com/Glaciohound/Chimera-ST/raw/main/chimera/resources/figs/method.png =100%x) This repository is up to now a nightly version, and is bug-prone because of code refactoring. […]

Read more
Visualization

Propuestas electorales de los candidatos a constituyentes, Chile 2021

textos-constituyentes propuestas electorales de los candidatos a constituyentes, Chile 2021 Programas descargados desde https://elecciones2021.servel.cl/informacion-general/ Metodología/Programación Inicialmente, bastaba con utilizar beautifulsoup + fitz en Python para descargar los archivos en formato PDF y extraer sus textos. Luego notamos que venían muchos vacíos, por corresponder a PDF escaneados (como el notable caso de una candidata del distrito 15 que subió su diploma). Para resolver este problema, recurrimos al servicio Transcribe de Amazon Cloud (con la librería boto3). GitHub https://github.com/sergiolucero/textos-constituyentes    

Read more
Deep Learning

Guide & Examples to create deep learning gstreamer plugins and use them in your pipeline

Guide & Examples to create deeplearning gstreamer plugins and use them in your pipeline Thanks to the work done by @jackersson. In this repository we have taken inspirations from: gstreamer-python gst-plugins-tf We have currently tested our code on Ubuntu 18.04. You can also refer to the official installation document for your linux flavor. Packages Required sudo apt install cmake m4 git build-essential sudo apt install libssl-dev libcurl4-openssl-dev liblog4cplus-dev Gstreamer Installation sudo apt-get install libgstreamer1.0-0 gstreamer1.0-plugins-base gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav gstreamer1.0-doc […]

Read more
Matplotlib

A Python library for plotting hockey rinks with Matplotlib

Hockey Rink A Python library for plotting hockey rinks with Matplotlib. Installation pip install hockey_rink Current Rinks The following shows the custom rinks currently available for plotting. from hockey_rink import NHLRink, IIHFRink, NWHLRink import matplotlib.pyplot as plt fig, axs = plt.subplots(1, 3, sharey=True, figsize=(12, 6), gridspec_kw={“width_ratios”: [1, 98.4/85, 1]}) nhl_rink = NHLRink(rotation=90) iihf_rink = IIHFRink(rotation=90) nwhl_rink = NWHLRink(rotation=90) axs[0] = nhl_rink.draw(ax=axs[0]) axs[1] = iihf_rink.draw(ax=axs[1]) axs[2] = nwhl_rink.draw(ax=axs[2]) The NWHL logo comes from the NWHL site. Customization There is also room […]

Read more
Machine Learning

A New, Interactive Approach to Learning Python

The Python Workshop This is the repository for The Python Workshop, published by Packt. It contains all the supporting project files necessary to work through the course from start to finish. Requirements and Setup To get started with the project files, you’ll need to: Install Jupyter on Windows, Mac, Linux Install Anaconda on Windows, Mac, Linux Install Docker About The Python Workshop More than just a Python guide for beginners, The Python Workshop takes you through the full spectrum of […]

Read more
Advanced, NLP, Text

Part 16 : Step by Step Guide to Master NLP – Topic Modelling using LSA

This article was published as a part of the Data Science Blogathon Introduction This article is part of an ongoing blog series on Natural Language Processing (NLP). In the previous article, we completed a basic technique of Topic Modeling named Non-Negative Matrix Factorization. So, In continuation of that part now we will start our discussion on another Topic modeling technique named Latent Semantic Analysis. So, In this article, we will deep dive into a Topic Modeling technique named Latent Semantic Analysis […]

Read more
Advanced, NLP, Text

Part 20: Step by Step Guide to Master NLP – Information Retrieval

This article was published as a part of the Data Science Blogathon Introduction This article is part of an ongoing blog series on Natural Language Processing (NLP). In the previous article, we completed our discussion on Topic Modelling Techniques. Now, in this article, we will be discussing an important application of NLP in Information Retrieval. So, In this article, we will discuss the basic concepts of Information Retrieval along with some of the models that are used in Information Retrieval. NOTE: […]

Read more
Beginner, Machine Learning, NLP, Python, Text

Bag-of-words vs TFIDF vectorization –A Hands-on Tutorial

This article was published as a part of the Data Science Blogathon Whenever we apply any algorithm to textual data, we need to convert the text to a numeric form. Hence, there arises a need for some pre-processing techniques that can convert our text to numbers. Both bag-of-words (BOW) and TFIDF are pre-processing techniques that can generate a numeric form from an input text. Bag-of-Words: The bag-of-words model converts text into fixed-length vectors by counting how many times each word appears. […]

Read more
Advanced, Classification, NLP, Project, Python, Structured Data, Supervised

Spam Detection – An application of Deep Learning

This article was published as a part of the Data Science Blogathon What each big tech company wants is the Security and Safety of its customers. By detecting spam alerts in emails and messages, they want to secure their network and enhance the trust of their customers. The official messaging app of Apple and the official chatting app of Google i.e Gmail is unbeatable examples of such applications where the process of spam detection and filtering works well to protect users […]

Read more
Python

Saving memory with Pandas 1.3’s new string dtype

When you’re loading many strings into Pandas, you’re going to use a lot of memory. If you have only a limited number of strings, you can save memory with categoricals, but that’s only helpful in a limited number of situations. With Pandas 1.3, there’s a new option that can save memory on large number of strings as well, simply by changing to a new column type. Let’s see how. Pandas’ different string dtypes Every pandas.Series, and every column in a […]

Read more
1 … 556 557 558 559 560 … 945