PyTorch Dataset for Speech and Music audio

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

Expressive Digital Signal Processing (DSP) package for Python

Python command line utility wrappers for Whispercpp and other speech-to-text utilities

Experimenting with Python and librosa to do Audio Event Detection

A collection of useful audio datasets and transforms for PyTorch.

a little GUI tool to render visualization videos of audio files

Simple Python audio transcriber using OpenAI's Whisper speech recognition model

get-audio-metadata.py is a python script to analyze a folder full of wav files and generate a CSV report containing various metadata including

Data manipulation and transformation for audio signal processing, powered by PyTorch

Python script for analyzing and tagging music files by key and BPM

A minimalistic web app to generate transciption for audio built using Python

Zalo AI Challenge - Music Genre Classification

Webcam capture using getUserMedia, the stream is recorded via js and saved using php in two files inside the folder /video, one file for video as .webm and one file for audio as .wav

Various ID3 tag-related operations on local audio files

Using Deep Learning to Categorize Music as Time Progresses Through Spectrogram Analysis

Use a Convolutional Neural Network to predict a instrument and the note being played.

Unsupervised blind source separation of mixed images and sounds with variational auto-encoders.

Understand of the fundamentals of digital signal processing for Machine Learning/Deep Learning applications.

Transcribe and translate audio to text using Whisper and DeepL.

Tools can detect the infos of tempo, beat, meter.

Today's Trending Values for EDM Production

This repo contains the source code of the first deep learning-base singing voice beat tracking system. It leverages WavLM and DistilHuBERT pre-trained speech models to create vocal embeddings and trains linear multi-head self-attention layers on top of them to extract vocal beat activations. Then, it uses HMM decoder to infer signing beats and tempo.

This repo contains the code to reproduce the paper "Enriched Music Representations with Multiple Cross-modal Contrastive Learning"