#
Starred repositories
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Python re-implementation of the (constrained) spectral clustering algorithms used in Google's speaker diarization papers.
Open source platform for the machine learning lifecycle
Docker files for deploying Marian in a Docker container.
Facebook Low Resource (FLoRes) MT Benchmark
Code for extracting parallel corpora from pmindia
Beyond Accuracy: Behavioral Testing of NLP models with CheckList
FSA/FST algorithms, differentiable, with PyTorch compatibility.
Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch
A library for Multilingual Unsupervised or Supervised word Embeddings
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
A repository with the code related to experiments around context-aware machine translation
A Unified Toolkit for Deep Learning Based Document Image Analysis
Avatars for Zoom, Skype and other video-conferencing apps.
Implementation of many Arabic NLP and CV projects. Providing real time experience using many interfaces like web, command line and notebooks.
AraVec is a pre-trained distributed word representation (word embedding) open source project which aims to provide the Arabic NLP research community with free to use and powerful word embedding mod…
Rasa UI is a frontend for the Rasa Framework
Tracking the progress in end-to-end speech translation
CoVoST: A Large-Scale Multilingual Speech-To-Text Translation Corpus (CC0 Licensed)
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
A simple and easy to use trainer to generate Rasa/Snips NLU datasets
Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Mirror of the Restoration of 1st Edition UNIX kernel sources from pdf document.
Pre-processing and training scripts for the Tarteel Dataset