Stars
Web application generating interactive and highly customizable maps
Codebase for 'ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining'
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A high-throughput and memory-efficient inference and serving engine for LLMs
A package for NeuCodec: a 50hz, 0.8kbps, 24kHz audio codec.
Exploratory analysis of Bayesian models with Python
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
Fast, flexible extraction of moral information from textual input data.
📝 python package to calculate readability statistics of a text object - paragraphs, sentences, articles.
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition [ACL 2023]
Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Loki: Open-source solution designed to automate the process of verifying factuality
FacTool: Factuality Detection in Generative AI
[ACL'24] Moral Emotion Dataset & Classifier
Shapley Interactions and Shapley Values for Machine Learning
Bivariate Shapley is a Shapley-based method of identifying directional feature interactions and feature redundancy
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
A python module for English lemmatization and inflection.
Accurately generate all possible forms of an English word e.g "election" --> "elect", "electoral", "electorate" etc.
Text Extraction Formulation + Feedback Loop for state-of-the-art WSD (EMNLP 2021)
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Label Studio is a multi-type data labeling and annotation tool with standardized output format