Unofficial implementation of NVIDIA P-Flow TTS paper

Speech Human Evaluation Estimation Toolkit (SHEET)

A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.

Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet

HuBERT content encoders for: A Comparison of Discrete and Soft Speech Units for Improved Voice Conversion

Unsupervised Rhythm Modeling for Voice Conversion

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

Official PyTorch implementation of BigVGAN (ICLR 2023)

Singing Voice Conversion Challenge 2023 Starter Kit: FastSVC Reimplementation

Pytorch implementation of stochastically quantized variational autoencoder (SQ-VAE)

Magenta: Music and Art Generation with Machine Intelligence

A high-quality speech analysis, manipulation and synthesis system

The Implementation of FastSpeech based on pytorch.

Provides training, inference and voice conversion recipes for RADTTS and RADTTS++: Flow-based TTS models with Robust Alignment Learning, Diverse Synthesis, and Generative Modeling and Fine-Grained …

Neural network-based singing voice synthesis library for research

AIを使ったリアルタイムボイスチェンジャー(Trainer)

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

Pytorch implementation of MixNMatch

Code for the paper Hybrid Spectrogram and Waveform Source Separation

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

page

Quasi-Periodic Parallel WaveGAN Pytorch implementation

Pytorch implementation of the CREPE pitch tracker