Hady Elsahar's repositories
audioseal-anon
Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector
audiocraft
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
wavmark
AI-based Audio Watermarking Tool
Template-AfricaNLP-Workshop
Template: AfricaNLP Workshop
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
Megatron-DeepSpeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
acl-anthology
Data and software for building the ACL Anthology.
Template-for-ICLR-2021-Workshop-on-Energy-Based-Models
Forked from https://github.com/ICLR/Master-Template/tree/master/iclr2021
transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
EBM-visualizations
notebooks of cool EBM visualizations
trl
Train transformer language models with reinforcement learning.
Awesome-Energy-Based-Models
learning material on energy based models
domain-shift-prediction
:eyeglasses: "To Annotate or Not Predicting Performance Drop under Domain Shift" EMNLP2019
awesome-reading-group
Agile reading group that works
gitignore
A collection of useful .gitignore templates
licenseclassifier
A License Classifier
bert_score
BERT score for text generation
Creative-Commons-Markdown
Markdown-formatted Creative Commons licenses
examples
Example deep learning projects that use wandb's features.
relation-discovery-2-entities
unsupervised relation discovery between two entities
comet-examples
Examples of Machine Learning code using Comet.ml
allennlp
An open-source NLP research library, built on PyTorch.
RE-NLG-Dataset
T-Rex : A Large Scale Alignment of Natural Language with Knowledge Base Triples
NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.