yzyouzhang

openpilot

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system in 275+ supported cars.

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

ai-audio-startups

Community list of startups working with AI in audio and music technology

s2cnn

Spherical CNNs

Awesome-Deepfakes-Detection

A list of tools, papers and code related to Deepfake Detection.

dla

Deep learning for audio processing

inspect_ai

Inspect: A framework for large language model evaluations

gill

🐟 Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".

spherical-cnn

Demo code for the paper "Learning SO(3) Equivariant Representations with Spherical CNNs"

FBPINNs

Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)

Pengi

An Audio Language model for Audio Tasks

MyVLM

Official Implementation for "MyVLM: Personalizing VLMs for User-Specific Queries" (ECCV 2024)

ml-spatial-librispeech

A large synthetic dataset of spatial audio with multiple labels

StyleTalk

Official release of StyleTalk dataset.

PartialSpoof

brian2hears

"Brian Hears" auditory modelling toolbox for the brian2 simulator

Child-ASR-Paper

A list of papers for child ASR

asvspoof5

audio_diarization_annotation

Audio Diarization Annotation tool

MultiOOD

Scaling Out-of-Distribution Detection for Multiple Modalities

1d-spectral-optimal-transport

An 1D optimal transport inspired loss function in the spectral domain. Can be used for improving frequency localization/estimation in differentiable digital signal processing. Experiments from paper: "Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport".

conformer-based-classifier-for-anti-spoofing

Implementation of "A conformer-based classifier for variable-length utterance processing in anti-spoofing" published in Interspeech 2023.

CtrSVDD_Utils

CtrSVDD2024_Baseline

Baseline system for SVDD 2024 Challenge CtrSVDD track

LAPChallenge

The LAP Challenge aims at advancing spatial audio technologies through the personalization of HRTFs.

nEMO

DeepFake-Detection

DeepFake Detection using Siamese Neural Networks

ragdoll-data-pipeline

TemporalIntegration