A production-ready implementation of WaveRNN-based autoregressive waveform synthesis.

Multilingual G2P in 100 languages

Noise reduction in python using spectral gating (speech, bioacoustics, audio, time-domain signals)

A Data Streaming Library for Efficient Neural Network Training

Typed command line interfaces with argparse and pydantic

Reference implementation of the ChordPro standard for musical lead sheets.

An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.

Simple package for binding functions to CLI or config files.

Learn make by example

Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

Speaker embedding (d-vector) trained with GE2E loss

Helpers for running native Python functions as qsub jobs on the CLSP grid

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a ca…

Haste: a fast, simple, and open RNN library

MADGRAD Optimization Method

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

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

[Prototype] Tools for the concurrent manipulation of variably sized Tensors.

Implementation of the AlignTTS

OpenShot Video Editor is an award-winning free and open-source video editor for Linux, Mac, and Windows, and is dedicated to delivering high quality video editing and animation solutions to the world.

List of speech synthesis papers.

Accompanying code for our paper "Optimizing Short-Time Fourier Transform Parameters via Gradient Descent"

Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer

Train/test a variety of open source vocoders using the same input features and dataset. Then infer together for easy side-by-side comparisons.

Python implementation of soft-DTW.

Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.