xiaomingnio

live2d-py

Live2D for Python (C++ Wrapper): Supports model loading, lip-sync and basic face rigging.

metahuman-stream

Real time interactive streaming digital human

MuseTalk

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

hallo

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

AI-Vtuber

一个高自由度的端到端的可定制AI-VTuber。支持对接哔哩哔哩直播间，以智谱API作为语言基座模型，拥有意图识别、长短期记忆（直接记忆和联想记忆），支持搭建认知库、歌曲作品库，接入了当前热门的一些语音转换、语音合成、图像生成、数字人驱动项目，并提供了一个便于操作的客户端。

duix.ai

LangSegment

It is a multi-lingual (97 languages) text content automatic recognition and segmentation tool. 强大的TTS多语言（97种语言）混合文本内容自动分词工具。

ui-voice-chatbot-gpt

Voice enabled chatbot with UI to display the conversation, powered by ChatGPT.

live2d-TTS-LLM-GPT-SoVITS-Vtuber

低成本的简单基于live2d TTS文字转语音和大模型聊天的直播解决方案

VirtualWife

VirtualWife是一个虚拟数字人项目，支持B站直播，支持openai、ollama

ChatTTS

A generative speech model for daily dialogue.

Lip_Wise

Orchestrating AI for stunning lip-synced videos. Effortless workflow, exceptional results, all in one place.

LabCD

遥感变化检测标注工具『Remote sensing change detection annotation tool』

trt_yolo_video_pipeline

TensorRT+YOLO系列的 多路 多卡 多实例 并行视频分析处理案例

EfficientSAM

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

Bert-VITS2

vits2 backbone with multilingual-bert

WeTextProcessing

Text Normalization & Inverse Text Normalization

kantts

TTS appalication based on modelscope KAN-TTS

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

PaddleSpeech

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

keypoint_annotation

This is a keypoints annotation tool using pure python.

PaddleSpeech-Streaming-ASR-Client

基于PaddleSpeech Server WebSocket API的流式语音识别客户端脚本

yolov8-pytorch_quantization

使用pytorch_quantization对yolov8进行量化

infer

A new tensorrt integrate. Easy to integrate many tasks

YOLOv5_ByteTrack_Multithreading_TensorRT

Multi-thread tracking of YOLOv5 and ByteTrack implemented by C++, accelerated by TensorRT. YOLOv5 和 ByteTrack 的多线程追踪 C++ 实现, 使用 TensorRT 进行推理加速

hand_cls

A hand classification using repvgg.

trt_repvgg_cls

A tensorrt infer implement for repvgg classification.

ACCV2022_FGIA_1st

1st solution for the Webly-supervised Fine-grained Recognition competition in https://www.cvmart.net/race/10412/base

tiny-tensorrt

Deploy your model with TensorRT quickly.

course

高性能并行编程与优化 - 课件