Code for the blog "Neural audio codecs: how to get audio into LLMs"

Simple tokenizer for English text

Interpretability for sequence generation models 🐛 🔍

Unofficial Python client library for Semantic Scholar APIs.

PyTorch implementation of the InfoNCE loss for self-supervised learning.

Structured state space sequence models

Reduce multiple PyTorch TensorBoard runs to new event (or CSV) files.

Aggregate multiple tensorboard runs to new summary or csv files

PyTorch GPU distributed training code for MIL-NCE HowTo100M

Code for the AVLnet (Interspeech 2021) and Cascaded Multilingual (Interspeech 2021) papers.

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

Problem Agnostic Speech Encoder

Wavenet Autoencoder for Unsupervised speech representation learning (after Chorowski, Jan 2019)

PyTorch implementation of VQ-VAE + WaveNet by [Chorowski et al., 2019] and VQ-VAE on speech signals by [van den Oord et al., 2017]

VQ-VAE implementation / pytorch

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

"My CEWE Photobook" MCF to PDF converter

Tensorflow Implementation of the paper [Neural Discrete Representation Learning](https://arxiv.org/abs/1711.00937) (VQ-VAE).

Code release for Hu et al. Segmentation from Natural Language Expressions. in ECCV, 2016

code for Learning Structured Text Representations

NYU ML² work on sentence encoding with tree structure and dynamic graphs

Using computer vision to ground unlabelled speech.

Code for paper "A learned representation of artist specific colourisation"

gentle forced aligner

A technical report on convolution arithmetic in the context of deep learning

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Recurrent Highway Networks - Implementations for Tensorflow, Torch7, Theano and Brainstorm