Signterpreter

American Sign Language (ASL) to Text Converter

Recommendations

Although there is grayscale and gaussian blur, we recommend that you use this application with a wall or greenscreen right behind you. It is not perfect at distinguishing behind hand gestures and different objects in the background.

Packages

You will need to download a few packages with the latest version of pip. By running the following code segment in command prompt, you should be able to run the application perfectly:

1. Latest pip -> pip install --upgrade pip

2. numpy -> pip install numpy

3. string -> pip install strings

4. os-sys -> pip install os-sys

5. opencv -> pip install opencv-python

6. tensorFlow -> i) pip install tensorflow 
                 ii) pip3 install --upgrade https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.8.0-cp34-cp34m-linux_x86_64.whl
7. keras -> pip install keras

8. tkinter -> pip install tk

9. PIL -> pip install Pillow

10. enchant -> pip install pyenchant (Python bindings for the Enchant spellchecking system)

11. hunspell -> pip install cyhunspell (A wrapper on hunspell for use in Python)

What is not Included

We have not attached our training and testing dataset due to the sheer amount of files. To create your own dataset to train and test the model, you will need to run the following applications by opening them or using command prompt:

1. FoldersCreation.py -> python FoldersCreation.py

2. TestingDataCollection.py -> python TestingDataCollection.py

3. TrainingDataCollection.py -> python TrainingDataCollection.py

American Sign Language (ASL) to Text Converter

Related tags

Overview

Signterpreter

Recommendations

Packages

What is not Included

Owner

Include MelGAN, HifiGAN and Multiband-HifiGAN, maybe NHV in the future.

This is the code for the EMNLP 2021 paper AEDA: An Easier Data Augmentation Technique for Text Classification

Use AutoModelForSeq2SeqLM in Huggingface Transformers to train COMET

DeepPavlov Tutorials

An extension for asreview implements a version of the tf-idf feature extractor that saves the matrix and the vocabulary.

Natural Language Processing

A minimal code for fairseq vq-wav2vec model inference.

Code for PED: DETR For (Crowd) Pedestrian Detection

A script that automatically creates a branch name using google translation api and jira api

Official codebase for Can Wikipedia Help Offline Reinforcement Learning?

Tensorflow implementation of paper: Learning to Diagnose with LSTM Recurrent Neural Networks.

An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

A PyTorch-based model pruning toolkit for pre-trained language models

Continuously update some NLP practice based on different tasks.

Analyse japanese ebooks using MeCab to determine the difficulty level for japanese learners

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Code for the Python code smells video on the ArjanCodes channel.

StarGAN - Official PyTorch Implementation

숭실대학교 컴퓨터학부 전공종합설계프로젝트

This library is testing the ethics of language models by using natural adversarial texts.