Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context Anchoring

July 31, 2021 By: Aitor Ormazabal, Mikel Artetxe, Aitor Soroa, Gorka Labaka, Eneko Agirre Abstract Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embeddings. Such methods critically rely on those embeddings having a similar structure, but it was recently shown that the separate training in different languages causes departures from this assumption. In this paper, we propose an alternative approach that does not have this limitation, while requiring a weak seed dictionary […]

Read more

Discord Bot for League of Legends live match tracker

SABot Dicord Bot for League of Legends match auto tracker. Features: Search Summoners statistics in League of Legends. Auto-notifications provide when summoner starts a match, and provide information of participations. Commands: *General commands !help !commands *LOL Search-informations !l match ‘SummonerName’ // live match info *LOL live-match-tracker !l setup !l add ‘SummonerName’ !l remove ‘SummonerName’ !l list !l start // start live-match-tracker !l stop // stop live-match-tracker How to set up your own bot: You need to install python packages with […]

Read more

Run object detection model on the Raspberry Pi

Raspberry-Pi-TF-Lite-Object-Detection Using TensorFlow Lite with Python is great for embedded devices based on Linux, such as Raspberry Pi. This is the guide for installing TensorFlow Lite on the Raspberry Pi and running pre-trained object detection models on it. Step 1. Setting up Rasperry Pi Upgrade Raspbian Stretch to Buster (If you on Buster, skip this step and simply run sudo apt-get update and sudo apt-get dist-upgrade) $ sudo apt-get update && sudo apt-get upgrade -y Verify nothing is wrong. Verify […]

Read more

A E-ink ticker that shows usefull information about bitcoin

bitcoin-ticker bitcoin-ticker is a E-ink ticker that shows usefull information about bitcoin. Due to the limited refresh lifetime, new information is currently shown every 5 minutes and whenever a new block arrives. Hardware I’m currently working on a 7.5 inch version with the following e-Paper: The config.ini needs the following settings when using the 7.5 inch: epd_type = 7in5_V2 orientation = 270 Usage Ticker view The Tickers the following information: Block height, Mean block intervall in minutes, Time Minimal Block […]

Read more

Toolkit for collecting and applying templates of prompting instances

PromptSource Toolkit for collecting and applying templates of prompting instances. WIP Setup Download the repo Navigate to root directory of the repo Install requirements with pip install -r requirements.txt Running From the root directory of the repo, you can launch the editor with streamlit run promptsource/promptsource.py There are 3 modes in the app: Helicopter view: aggregate high level metrics on the current state of the sourcing Prompted dataset viewer: check the templates you wrote or already written on entire dataset […]

Read more

A Simplified Automated CLI tool for GIT

GitFun A Simplified Automated CLI tool for GIT, It’s for Lazy Developers and Newbies Installation It’s simple step to install Pre-requisites: Python > = 3.7 Python Package Installer(PyPI) pip install gitfun For initial push to the remote Repository fun pushbranch -url -m commit message -b branch name For checking the git status fun status For checking the remote fun remote For getting a pull from the branch fun pullbranch -url -b branch name for development setup clone the repository git […]

Read more

Upgrade MIB2 STD ZR Firmware without Navigation

mib2std-zr-firmware-upgrade This repository contains some scripts and documentation how to upgrade the MIB2 firmware to a different HW train (e.g.: 02xx -> 03xx, 04xx). The documentation is for the Technisat MIB2 STD unit without navigation. It describes how to patch the swdownload binary, that the unit accepts updates for a higher HW train.In addition to this repository it’s required to have access to the MIB Solutions folder on MEGA.nz (Link can be found in various forums and is changing from […]

Read more

A python script for 1-D array data classification

Keras-1D-NN-Classifier This code is based on the reference codes linked below. reference 1, reference 2 This code is for 1-D array data classification. The given data in ‘data’ directory is simple data for training and testing this code. About this code This code is iterated by changing the’learn rate’ variable to find the optimal learning rate. The related part is the code below. var = [ 4e-5,8e-5, 12e-5] for i in range(len(var)): var_str = ‘lr replay %d th’ % i […]

Read more

Unofficial TensorFlow implementation of the Keyword Spotting Transformer model

Keyword Spotting Transformer This is the unofficial TensorFlow implementation of the Keyword Spotting Transformer model. This model is used to train on the 35 words speech command dataset Paper : Keyword Transformer: A Self-Attention Model for Keyword Spotting Model architecture Download the dataset To download the dataset use the following command wget https://storage.googleapis.com/download.tensorflow.org/data/speech_commands_v0.02.tar.gz mkdir data mv ./speech_commands_v0.02.tar.gz ./data cd ./data tar -xf ./speech_commands_v0.02.tar.gz cd ../ Setup virtual environment virtualenv -p python3 venv source ./venv/bin/activate Install dependencies pip install -r requirements.txt […]

Read more

AI and Machine Learning workflows on Anthos Bare Metal

AI and Machine Learning workflows using TensorFlow on Anthos Bare Metal. TensorFlow is one of the most popular ML frameworks (10M+ downloads per month) in use today, but at the same time presents a lot of challenges when it comes to setup (GPUs, CUDA Drivers, TF Serving etc), performance tuning, cluster provisioning, maintenance, and model serving. This work will showcase the easy to use guides for ML model serving, training, infrastructure, ML Notebooks, and more on Anthos Bare Metal. Terraform […]

Read more
1 2 3 52