Stars
Google Research
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…
Tacotron 2 - PyTorch implementation with faster-than-realtime inference
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
IPython kernel for Torch with visualization and plotting
PyTorch implementation of GAN-based text-to-speech synthesis and voice conversion (VC)
TensorFlow implementation for audio neural style.
Collection of notebooks and scripts related to audio processing and machine learning.
Implementation of WaveGrad high-fidelity vocoder from Google Brain in PyTorch.
PyTorch implementation of Tacotron speech synthesis model.
MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms
Download the MusicCaps dataset for music captioning
Run your own DeepStyle factory on the cloud.
MelGAN implementation with Multi-Band and Full Band supports...
Wavenet and its applications with Tensorflow
2018/2019 TTS framework integrating state of the art open source methods
WaveNet for the separation of audio sources
A Universal Music Translation Network Implementation
Generating audio from qubits, using Qiskit.
Repository for my scientific initiation project on audio thumbnailing.