Angelo Mendes's starred repositories
unstructured
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
Introduction-GNN
Esse repositorio é para o curso de difusão ofericido pelo ICMC/USP Introdução às redes neurais em grafos e suas aplicações em tarefas de aprendizado de máquina.
seamless_communication
Foundational Models for State-of-the-Art Speech and Text Translation
ACA-Slides
Slides and Code for "An Introduction to Audio Content Analysis," also taught at Georgia Tech as MUSI-6201. This introductory course on Music Information Retrieval is based on the text book "An Introduction to Audio Content Analysis", Wiley 2012/2022
Multi_Comparison_Matrix
Multi Comparison Matrix: A long term approach to benchmark evaluations
MARBLE-Benchmark
Music Audio Representation Benchmark for Universal Evaluation
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.
CS6208_2023
Advanced Topics in Artificial Intelligence, NUS CS6208, 2023
Twin_Causal_Nets
Estimating the probabilities of caution via deep monotonic twin networks
vector-quantize-pytorch
Vector (and Scalar) Quantization, in Pytorch
MLPInit-for-GNNs
[ICLR 2023] MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.