Brij Mohan Lal Srivastava's starred repositories
loss-landscape
Code for visualizing the loss landscape of neural nets
Bayesian-Neural-Networks
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
portio-hugo
Portio Hugo is a simple, minimal and responsive Portfolio Hugo Theme. Portio Hugo is well organized, well-formatted, and named accordingly so it’s easy to change any and all of the design. Portio is built with Bootstrap 4. You can customize it very easily to fit your needs.
Stein-Variational-Gradient-Descent
code for the paper "Stein Variational Gradient Descent (SVGD): A General Purpose Bayesian Inference Algorithm"
carbontracker
Track and predict the energy consumption and carbon footprint of training deep learning models.
tikz_favorites
collection of favorite TikZ graphics
sequitur-g2p
This is a github repository of the abandonware Sequitur G2P by Bisani & Ney
Factorized-TDNN
PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi
collateral-learning
Collateral Learning - Functional Encryption and Adversarial Training on partially encrypted networks
wav-audio-encoder-js
Waveform Audio encoder for browsers
pytorch-ivectors
GPU accelerated implementation of i-vector extractor training using PyTorch. Requires Kaldi for feature extraction and UBM training. An example script is provided for VoxCeleb data.
Voice-Privacy-Challenge-2022
Baseline Recipe for VoicePrivacy Challenge 2022: anonymization systems and evaluation software
Voice-Privacy-Challenge-2020
Baseline Recipe for VoicePrivacy Challenge 2020: https://www.voiceprivacychallenge.org/vp2020/docs/VoicePrivacy_2020_Eval_Plan_v1_3.pdf
INTERSPEECH19_TUTORIAL
Interspeech 2019 tutorial materials
INMT-lite
Interactive Neural Machine Translation-lite (INMT-lite) is a framework to train and develop lite versions (.tflite) of models for neural machine translation (NMT) that can be run on embedded devices like mobile phones and tablets that have low computation power and space. The tflite models generated can be used to build the offline version of INMT mobile, a mobile version of INMT web.
SA-toolkit
SA-toolkit: Speaker speech anonymization toolkit in python
phd-thesis-template
Template for PhD thesis using Tufte's style book