Code for the paper Hybrid Spectrogram and Waveform Source Separation

so-vits-svc fork with realtime support, improved interface and more features.

vits2 backbone with multilingual-bert

Simultaneous speech-to-text model

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

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

🔥 2D and 3D Face alignment library build using pytorch

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Official repo for consistency models.

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

On-device TTS model by Neuphonic

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

Vector (and Scalar) Quantization, in Pytorch

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

zero-shot voice conversion & singing voice conversion, with real-time support

Have a natural, spoken conversation with AI!

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

A python package to analyze and compare voices with deep learning

AudioLDM: Generate speech, sound effects, music and beyond, with text.

A simple, high-quality voice conversion tool focused on ease of use and performance.

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

Text-to-Audio/Music Generation

Offline Text To Speech synthesis for python

WaveNet vocoder

Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

Longformer: The Long-Document Transformer

Audio generation using diffusion models, in PyTorch.

VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning