llama3 implementation one matrix multiplication at a time

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

NYU Deep Learning Spring 2020

A library for debugging/inspecting machine learning classifiers and explaining their predictions

NYU Deep Learning Spring 2021

Companion repository for the book Building Machine Learning Powered Applications

A series of tutorial notebooks on denoising diffusion probabilistic models in PyTorch

Implementation of WaveGrad high-fidelity vocoder from Google Brain in PyTorch.

Transformers 3rd Edition

Example projects built with the Hume AI APIs

GuitarSet: a dataset for guitar transcription

A PyTorch implementation of "WaveFlow: A Compact Flow-based Model for Raw Audio" (ICML 2020)

Deep Learning for Speech

Code and data for the Transformer neural network trained to translate between molecular text representations and create molecular embeddings.

Speaker diarization with GMM-UBM and MAP Adaptation

Constant-Q harmonic coefficients (CQHCs), a timbre feature designed for music signals.

Tensorflow implementation of pix2pix for creating music from a voice. Vocals2Song.

This repository contains the code for the paper: "DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances"

Введение в ArcGIS API for python

This repository provides a solution to the challenge of verifying audio tracks containing crying babies, as presented in the CryCeleb2023 challenge

Code to download AudioSet dataset, modified to download VGGsound dataset.

Cross-Caps Lab's Winning System Submission for CryCeleb23 Challenge