facebookresearch / SING
Symbol-to-Instrument Neural Generator
☆160Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for SING
- The code for the MaD TwinNet. Demo page:☆111Updated last year
- Pytorch Implementation of FFTNet☆86Updated 6 years ago
- TiFGAN: Time Frequency Generative Adversarial Networks☆114Updated 2 years ago
- Vector Quantized Contrastive Predictive Coding for Template-based Music Generation☆79Updated last year
- NIPS2017 "Time Domain Neural Audio Style Transfer" code repository☆140Updated 2 years ago
- SiSEC MUS 2018 Submission System☆43Updated 5 years ago
- learning audio effects with neural networks☆102Updated last year
- Code accompanying the paper "Semi-supervised adversarial audio source separation applied to singing voice extraction"☆83Updated 5 years ago
- PyTorch reimplementation of WaveGAN☆57Updated 2 years ago
- Tensorflow implementation of the models used in "End-to-end learning for music audio tagging at scale"☆148Updated 5 years ago
- Fatcord's Alternative WaveRNN (Faster training)☆126Updated 5 years ago
- Vocode spectrograms to audio with generative adversarial networks☆63Updated 5 years ago
- parallel wavenet based on nsynth☆106Updated 5 years ago
- FFTNet vocoder implementation☆81Updated 6 years ago
- A fast cnn-based vocoder☆78Updated 4 years ago
- A WaveNet-based vocoder for fast inference☆161Updated 6 years ago
- A PyTorch implementation of the WaveGlow: A Flow-based Generative Network for Speech Synthesis☆206Updated 6 years ago
- ☆76Updated 4 years ago
- ISMIR 2020 Paper repo: Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm☆81Updated last year
- A PyTorch implementation of "WaveFlow: A Compact Flow-based Model for Raw Audio" (ICML 2020)☆120Updated 3 months ago
- A simplified PyTorch implementation of GANsynth☆81Updated 5 years ago
- A WaveRNN implementation☆198Updated 5 years ago
- Supplementary material of "Deep Unsupervised Drum Transcription", ISMIR 2019☆125Updated 3 months ago
- Implementation of the Griffin and Lim algorithm to recover an audio signal from a magnitude-only spectrogram.☆169Updated 6 years ago
- 2018/2019 TTS framework integrating state of the art open source methods☆47Updated 5 years ago
- ☆67Updated 5 years ago
- Training neural audio classifiers with few data − https://arxiv.org/abs/1810.10274☆60Updated 5 years ago
- Multi-voice singing voice synthesis☆235Updated last year
- It is a Tutorial, not a complete implement☆55Updated 6 years ago
- Tensorflow implementation of SampleRNN☆141Updated 4 years ago