Stars
Robust Speech Recognition via Large-Scale Weak Supervision
💫 Industrial-strength Natural Language Processing (NLP) in Python
Deezer source separation library including pretrained models.
Faker is a Python package that generates fake data for you.
Bringing Old Photo Back to Life (CVPR 2020 oral)
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
A data augmentations library for audio, image, text, and video.
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Beautiful visualizations of how language differs among document types.
Large Concept Models: Language modeling in a sentence representation space
Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.
💥 Use the latest Stanza (StanfordNLP) research models directly in spaCy
A bidirectional recurrent neural network model with attention mechanism for restoring missing punctuation in unsegmented text
Hierarchical unsupervised and semi-supervised topic models for sparse count data with CorEx
Mnemosyne: efficient learning with powerful digital flash-cards.
Concurrently detect the minimum Python versions needed to run code
An evolving list of electronic media data sets used to model mental-health status.
Annotated dataset of 100 works of fiction to support tasks in natural language processing and the computational humanities.
TweetNLP for all the NLP enthusiasts working on Twitter! The Python library tweetnlp provides a collection of useful tools to analyze/understand tweets such as sentiment analysis, emoji prediction,…
TopicGPT: A Prompt-Based Framework for Topic Modeling (NAACL'24)
data⎰describe: Pythonic EDA Accelerator for Data Science
Code for collecting, processing, and preparing datasets for the Common Pile
Python library for Representational Similarity Analysis
Repository containing codes and dataset access instructions for the EMNLP 2020 paper on empathy in text-based mental health support