Faster Whisper transcription with CTranslate2

Latex code for making neural networks diagrams

The goal of this library is to generate more helpful exception messages for matrix algebra expressions for numpy, pytorch, jax, tensorflow, keras, fastai.

Clone a voice in 5 seconds to generate arbitrary speech in real-time

🏡 Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

✍️ A carefully curated list of NLP paper summaries

Leaderboard implementations for datasets produced by the Mosaic Team.

Code and data accompanying Natural Language Processing with PyTorch published by O'Reilly Media https://amzn.to/3JUgR2L

PyTorch Tutorial materials for Duke University +Data Science Initiative

PyTorch Tutorial materials for Duke University +Data Science Initiative

Materials for +DataScience In-Person Learning Experiences (IPLEs)

Tools to download and cleanup Common Crawl data

Streamlit — A faster way to build and share data apps.

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

An open clone of the GPT-2 WebText dataset by OpenAI. Still WIP.

Ongoing research training transformer models at scale

Just draw a bounding box and you can remove the object you want to remove.

XLNet: Generalized Autoregressive Pretraining for Language Understanding

A mix of GAN implementations including progressive growing

Code and documentation for my Eyeo Festival talk 2019

Code for the paper "Language Models are Unsupervised Multitask Learners"

Dataset of GPT-2 outputs for research in detection, biases, and more

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

NLP research experiments, built on PyTorch within the AllenNLP framework.

PyTorch deep learning models for document classification

A very simple framework for state-of-the-art Natural Language Processing (NLP)

Code and test data for "On Measuring Bias in Sentence Encoders", to appear at NAACL 2019.