Official inference framework for 1-bit LLMs

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

🔊 Text-Prompted Generative Audio Model

リアルタイムボイスチェンジャー Realtime Voice Changer

speech self-supervised representations

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

The reproduced code for Google's SoundStorm

text to speech using autoregressive transformer and VITS

vits2 backbone with multilingual-bert

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

A python binding for mecab-ko

g2pK: g2p module for Korean

Korean grapheme-to-phone conversion in Python

0️⃣1️⃣🤗 BitNet-Transformers: Huggingface Transformers Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch with Llama(2) Architecture

식탁보 프로젝트

Unofficial pytorch implementation of BigVGAN: A Universal Neural Vocoder with Large-Scale Training

The official implementation of HierSpeech++

NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis

Unofficial implementation of NANSY++ in Pytorch Lightning

Official PyTorch implementation of BigVGAN (ICLR 2023)

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Blendshape and kinematics calculator for Mediapipe/Tensorflow.js Face, Eyes, Pose, and Finger tracking models.

Use VRM on Three.js

A real-time motion capture system for 3D virtual character animating.

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

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

Singing Voice Conversion via diffusion model

Robust Speech Recognition via Large-Scale Weak Supervision

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