Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

SOTA Open Source TTS

The source code of "DINet: deformation inpainting network for realistic face visually dubbing on high resolution video."

Foundational model for human-like, expressive TTS

Barkify: an unoffical training implementation of Bark TTS by suno-ai

Instant voice cloning by MIT and MyShell. Audio foundation model.

Easily train a good VC model with voice data <= 10 mins!

The Open Source Code of UniAudio

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

Implementation of Spear-TTS - multi-speaker text-to-speech attention network, in Pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

An unofficial PyTorch implementation of the audio LM VALL-E

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

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

🔊 Text-Prompted Generative Audio Model

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Official PyTorch implementation of BigVGAN (ICLR 2023)

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

Leaf: A Benchmark for Federated Settings

Facebook AI Research's Automatic Speech Recognition Toolkit

KenLM: Faster and Smaller Language Model Queries

PyTorch CTC Decoder bindings

Python interface to the WebRTC Voice Activity Detector

🦉 Data Versioning and ML Experiments

A Python package to assess and improve fairness of machine learning models.

GPU accelerated implementation of i-vector extractor training using PyTorch. Requires Kaldi for feature extraction and UBM training. An example script is provided for VoxCeleb data.

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding a…

COre Variable Feature Extraction Feature Extractor

Data manipulation and transformation for audio signal processing, powered by PyTorch