Audio transformations library for PyTorch

Steerable discovery of neural audio effects

Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch

A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.

MT3: Multi-Task Multitrack Music Transcription

🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time

Muzic: Music Understanding and Generation with Artificial Intelligence

Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)

Python library for rapid prototyping of environmental sound analysis systems

DALI: a large Dataset of synchronised Audio, LyrIcs and vocal notes.

Python library for working with Music Information Retrieval datasets

A python script for extracting loops from audio files.

Hierarchical fast and high-fidelity audio generation

Code for ISMIR 2020 paper: "Multiple F0 Estimation in Vocal Ensembles using Convolutional Neural Networks"

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

Code for the paper "Jukebox: A Generative Model for Music"

Find similar audio files easily

Code for the paper Hybrid Spectrogram and Waveform Source Separation

DDSP: Differentiable Digital Signal Processing

MelGAN vocoder (compatible with NVIDIA/tacotron2)