bhigy

zr-2021vg_baseline

Baselines for the Zero-Resources Speech Challenge using VisuallyGrounded Models of Spoken Language, 2021 edition

textual-supervision

Code for the paper "Textual supervision for visually grounded spoken language understanding".

discrete-repr

Accompanying code for the paper "Discrete representations in neural models of spoken language" (https://aclanthology.org/2021.blackboxnlp-1.11)

ai-deadlines

:alarm_clock: AI conference deadline countdowns

ASL-Alphabet-Translation

Using CNN to translate the ASL Alphabet

bhigy.github.io

My personal website

CodeMirror

In-browser code editor

CPC_audio

An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

deepspeech.pytorch

Speech Recognition using DeepSpeech2.

dropbox-restore

Restore any dropbox folder to a previous state

espnet

End-to-End Speech Processing Toolkit

kaldi

This is now the official location of the Kaldi project.

liveoverflow

Following liveoverflow binary exploitation playlist

matutils

Utilities for matlab

minimal-mistakes

:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.

natural-speech

This repository contains a codebase to build automatic speech recognition (ASR) systems for iCub and run them within YARP. It also proposes new articulatory-based and unsupervised models for ASR.

nbdev

Create delightful software with Jupyter Notebooks

OTFR

On the fly tactile and visual recognition for iCub

pafy

Python library to download YouTube content and retrieve metadata

polyglot

Color, ASCII-only Git prompt for zsh, bash, ksh93, mksh, pdksh, dash, and busybox ash

pydub

Manipulate audio with a simple and easy high level interface

revai-python-sdk

Rev AI Python SDK

silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

StreamingSpeakerDiarization

Lightweight python library for speaker diarization in real time implemented in pytorch

symbolic-bias

Code for the paper: Symbolic inductive bias for visually grounded learning of spoken language

tactile_objrec_mat

tiddlywiki_to_joplin

Script to convert a TiddlyWiki note export CSV file into a Joplin JEX file for import.

yarp

YARP - Yet Another Robot Platform

ZeroSpeech

VQ-VAE for Acoustic Unit Discovery and Voice Conversion