magenta / ddsp
DDSP: Differentiable Digital Signal Processing
☆3,019Updated 7 months ago
Alternatives and similar repositories for ddsp:
Users that are interested in ddsp are comparing it to the libraries listed below
- A toolkit for symbolic music generation☆476Updated 2 months ago
- Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch☆471Updated last year
- Utility functions for handling MIDI data in a nice/intuitive way.☆934Updated 5 months ago
- Python audio and music signal processing library☆1,423Updated 8 months ago
- WaveGAN: Learn to synthesize raw audio with generative adversarial networks☆1,353Updated 2 years ago
- CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)☆1,221Updated 8 months ago
- Realtime DDSP Neural Synthesizer and Effect☆754Updated last year
- a list of demo websites for automatic music generation research☆699Updated last week
- MIDI / symbolic music tokenizers for Deep Learning models 🎶☆772Updated 2 weeks ago
- Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder☆1,491Updated 2 weeks ago
- "Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions", ACM Multimedia 2020☆574Updated 2 years ago
- A serializable note sequence representation and utilities.☆228Updated 2 months ago
- Implementation of the Wave-U-Net for audio source separation☆890Updated 2 years ago
- Digital Audio Workstation with Python; VST instruments/effects, parameter automation, FAUST, JAX, Warp Markers, and JUCE processors☆1,011Updated 3 months ago
- Magenta Studio is a collection of music plugins built on Magenta’s open source tools and models☆1,102Updated 2 months ago
- Open-Unmix - Music Source Separation for PyTorch☆1,368Updated 10 months ago
- Audio processing by using pytorch 1D convolution network☆1,064Updated last year
- DeepAFx-ST - Style transfer of audio effects with differentiable signal processing. Please see https://csteinmetz1.github.io/DeepAFx-ST/☆385Updated last year
- Pronounced as "musician", musicnn is a set of pre-trained deep convolutional neural networks for music audio tagging.☆638Updated last year
- Python library for working with Music Information Retrieval datasets☆378Updated last week
- GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis☆1,005Updated last year
- Evaluation functions for music/audio information retrieval/signal processing algorithms.☆642Updated 2 months ago
- Community list of startups working with AI in audio and music technology☆1,651Updated 3 months ago
- Collection of audio-focused loss functions in PyTorch☆775Updated 9 months ago
- Audio super resolution using neural networks☆1,224Updated last year
- The PyTorch-based audio source separation toolkit for researchers☆2,370Updated 4 months ago
- Singing synthesis from MIDI file☆278Updated 2 years ago
- Fast Infinite Waveform Music Generation☆674Updated 2 years ago
- Join the community on Discord for more discussions around Neutone! https://discord.gg/VHSMzb8Wqp☆498Updated last month
- Python DSP module☆1,359Updated last month