Efficient Training of Audio Transformers with Patchout
-
Updated
Jan 12, 2024 - Python
Efficient Training of Audio Transformers with Patchout
This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.
Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"
Freesound Audio Tagging 2019
Urban sound source tagging from an aggregation of four second noisy audio clips via 1D and 2D CNN (Xception)
Implementation and reviews of Audio & Computer vision related papers in python using keras and tensorflow.
Training code of Cornell Birdcall Identification Challenge 6th place solution
Author's repository for reproducing DcaseNet, an integrated pre-trained DNN that performs acoustic scene classification, audio tagging, and sound event detection. Implemented using PyTorch.
6th place solution to Freesound Audio Tagging 2019 kaggle competition
Python library for rapid prototyping of environmental sound analysis systems
Easy to use Audio Tagging in PyTorch
Cloned from AlexeyAB/darknet, try to a spectrogram detector.
A birdcall dataset with manual data tagging
Emacs major mode for editing file tags (id3, etc)
An audio tag editor. For primary repo visit: https://gitlab.com/bmreading/metanote
Extended repository w. Cnn14, ResNet38 & Wavegram-LogMel_Cnn14 models for Audio Tagging
Scripts to process Google's Audioset
Automatically download and tag Deezer tracks, albums and playlists, using free-mp3-download.net
Add a description, image, and links to the audio-tagging topic page so that developers can more easily learn about it.
To associate your repository with the audio-tagging topic, visit your repo's landing page and select "manage topics."