Pytorch port of Google Research's VGGish model used for extracting audio features.

Audio classification with VGGish as feature extractor in TensorFlow

A library built for easier audio self-supervised training, downstream tasks evaluation

📁 This repo makes it easy to download the raw audio files from AudioSet (32.45 GB, 632 classes).

Unofficial Implementation of Google Deepmind's paper `Objects that Sound`

Sound augmentation using Large-scale audio dataset (Audioset)

This package aims at simplifying the download of the AudioSet dataset.

🎵 A repository for manually annotating files to create labeled acoustic datasets for machine learning.

Machine learning model for bird songs recognition

Spoken Language Identification on Common Voice and AudioSet using Deep Learning

Download audioset data super fastly with youtube-dl, ffmpeg and python multiprocessing

The unofficial implementation of paper, "Objects that Sound", from ECCV 2018.

📊 Easily apply audio-related machine learning models trained on the AudioSet dataset (527+ models/classes).

A VGGish-based DNN trained on the Watkins Marine Mammal Sound Database, with transfer learning from Audioset, to detect multiple marine mammal species.

[AAAI 2023 (Oral)] CrissCross: Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity

Continual Learning with Gated Incremental Memories for Sequential Data Processing. IJCNN 2020. Continual Learning with Recurrent Neural Networks (RNNs) inspired by Progressive network architecture.

Repo accompanying the blog post "How to Deploy A State-of-the-art PyTorch Model to iOS via Core ML (Part 3)".

Repo accompanying the blog post "How to Deploy PyTorch Models with Core ML Conversion Issues"

Codebase for Imperial MSc AI Individual Project - Self-Supervised Learning for Audio Inference

AudioSet classification using RNN