🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

A community-maintained Python framework for creating mathematical animations.

SOTA Open Source TTS

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

PyScript is an open source platform for Python in the browser. Try PyScript: https://pyscript.com Examples: https://tinyurl.com/pyscript-examples Community: https://discord.gg/HxvBtukrg2

🦉 Data Versioning and ML Experiments

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

Library for building WebSocket servers and clients in Python

The #1 open-source voice interface for desktop, mobile, and ESP32 chips.

On-device wake word detection powered by deep learning

Nginx UI allows you to access and modify the nginx configurations files without cli.

Sequence modeling benchmarks and temporal convolutional networks

😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

A python package to analyze and compare voices with deep learning

The PyTorch-based audio source separation toolkit for researchers

Self-Supervised Speech Pre-training and Representation Learning Toolkit

This library provides common speech features for ASR including MFCCs and filterbank energies.

Graph Neural Networks with Keras and Tensorflow 2.

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Keras Temporal Convolutional Network. Supports Python and R.

PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models

DELTA is a deep learning based natural language and speech processing platform. LF AI & DATA Projects: https://lfaidata.foundation/projects/delta/

the open-source virtual assistant for Ubuntu based Linux distributions

This is now the official location of the Merlin project.

CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)

General Speech Restoration

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

SincNet is a neural architecture for efficiently processing raw audio samples.