yaleimeng

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

v2rayNG

A V2Ray client for Android, support Xray core and v2fly core

hiddify-next

Multi-platform auto-proxy client, supporting Sing-box, X-ray, TUIC, Hysteria, Reality, Trojan, SSH etc. It’s an open-source, secure and ad-free.

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

ClashMetaForAndroid

A rule-based tunnel for Android.

NekoBoxForAndroid

NekoBox for Android / sing-box / universal proxy toolchain for Android

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

bisheng

Bisheng is an open LLM devops platform for next generation AI applications.

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

AniPortrait

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

oblivion-desktop

Oblivion Desktop - Unofficial Warp Client for Windows/Mac/Linux

Sub

自用clash订阅链接

video-subtitle-remover

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

swift

ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 35+ MLLMs. (Qwen, GLM4, Internlm2, Yi, Llama3, Llava, Deepseek, ...)

GKD_THS_List

GKD第三方订阅收录名单

MuseTalk

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

GeneFacePlusPlus

GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code

SyncTalk

[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"

chinese_speech_pretrain

chinese speech pretrained models

panda-vpn-pro

🚁🚀 熊猫VPN（PandaVPNPro）已确定跑路！快连VPN ，小牛加速器（小牛VPN）体验不佳且价格贵。低价机场，便宜机场，平价机场，廉价机场，翻墙机场，付费机场，收费机场，高速机场，稳定机场，性价比机场，优质机场推荐。翻墙，科学上网，梯子。非永久免费梯子，非永久免费VPN，非免费机场！谷歌，油管。适用Clash，V2RAY，小火箭等代理软件。🚀🚁

HeyGenClone

A simple and open-source analogue of the HeyGen system

Real3DPortrait

Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis; ICLR 2024 Spotlight; Official code

TrojanLinks

自动获取Trojan、vmess、vless、ss、SSR、openvpn，免费节点，订阅，科学上网，梯子

InternEvo

vosk-tts

Text To Speech Synthesis with Vosk

DINet_optimized

An optimized pipeline for DINet reducing inference latency for up to 60% 🚀. Kudos for the authors of the original repo for this amazing work.

lip_mask

通过此代码可以免训练模型并通过轻量级服务器定制数字人形象

HiQA

Code implement reposity of Paper HiQA

digitalAvatarRealtime

基于DINet的推理服务，推理视频流和视频