An Open Source Machine Learning Framework for Everyone

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Open Source Computer Vision Library

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

The Julia Programming Language

Clone a voice in 5 seconds to generate arbitrary speech in real-time

A high-quality speech analysis, manipulation and synthesis system

Magenta: Music and Art Generation with Machine Intelligence

[ICLR2026] VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

kaldi-asr/kaldi is the official location of the Kaldi project.

A tokenizer, text cleaner, and phonemizer for many human languages.

Mono open source ECMA CLI, C# and .NET implementation.

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

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

A list of popular github projects related to deep learning

🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

x86-64 assembler embedded in Python

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

DeepMind's Tacotron-2 Tensorflow implementation

Edinburgh Speech Tools

Caffe2 is a lightweight, modular, and scalable deep learning framework.

NeMo: a toolkit for conversational AI

header only, dependency-free deep learning framework in C++14

Swift for TensorFlow

Frontend system for HMM-based speech synthesis models generated by HTS.

WaveNet-Vocoder implementation with pytorch.

This is now the official location of the Merlin project.

MagPhase Vocoder: Speech analysis/synthesis system for TTS and related applications.