Code for vec2wav 2.0, a speech token vocoder for VC. Paper: https://arxiv.org/abs/2409.01995

Awesome music generation model——MG²

first base model for full-duplex conversational audio

Fast and accurate automatic speech recognition (ASR) for edge devices

The fastest digital human algorithm, now on your desktop.

PyTorch implementation of the Differential-Transformer architecture for sequence modeling, specifically tailored as a decoder-only model similar to large language models (LLMs). The architecture in…

一个超轻量级、可以在移动端实时运行的数字人模型

GLM-4-Voice | 端到端中英语音对话模型

Human Motion Video Generation: A Survey (https://www.techrxiv.org/users/836049/articles/1228135-human-motion-video-generation-a-survey)

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

Pseudo Streaming SenseVoice with Hotwords

Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

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

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

An Open-Sourced LLM-empowered Foundation TTS System

Open source inference code for Rev's model

Implementation of Liquid Nets in Pytorch

JoyHallo: Digital human model for Mandarin

开源的SSL证书管理工具，可以帮助你自动申请、部署SSL证书，并在证书即将过期时自动续期。An open-source SSL certificate management tool that helps you automatically apply for and deploy SSL certificates, as well as automatically renew them w…

[INTERSPEECH'24] Official repository for "MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset"

The official implementation of RealisDance

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice