Stars
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …
这是一个用C++实现ASR推理的项目,它依赖很少,安装也很简单,推理速度很快,在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来,数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小时), 所以识别效果也很好,可以媲美许多商用的ASR软件。
[SDM 2022] Towards Similarity-Aware Time-Series Classification
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
A machine learning library for detecting anomalies in signals.
Repository of the Tranferlab Practical Anomaly Detection workshop
The fundamental package for AIops with python.
Time series anomaly detection algorithm implementations for TimeEval (Docker-based)
The machine learning toolkit for time series analysis in Python
很多镜像都在国外。比如 gcr 。国内下载很慢,需要加速。致力于提供连接全世界的稳定可靠安全的容器镜像服务。
AKGR: Awesome Knowledge Graph Reasoning is a collection of knowledge graph reasoning works, including papers, codes and datasets
Collection of slides, repositories, papers about AIOps
Metis is a learnware platform in the field of AIOps.
Contains the development for the Industry 4.0 standards knowledge graph (I40KG). Its current collaborative development is driven by VoCol - http://vocol.iais.fraunhofer.de/sto/
Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
The Prometheus monitoring system and time series database.
pycorrector is a toolkit for text error correction. 文本纠错,实现了Kenlm,T5,MacBERT,ChatGLM3,LLaMA等模型应用在纠错场景,开箱即用。
带HTTP API的数字人视频播放器,使用gradio api对接Easy-Wav2Lip、Sadtalker、GeneFacePlusPlus、MuseTalk,也可以用于播放本地视频
MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting
🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
[ACM MM 2024] This is the official code for "AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding"
本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形,设置面部区域可配置的增强方式进行合成唇形(人脸)区域画面增强,提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧,补充帧间合成唇形的动作过渡,使合成的唇形更为流畅、真实以及自然。
Open Source framework for voice and multimodal conversational AI
LlamaIndex is a data framework for your LLM applications
Analysis of CWRU Bearing Data Set and Development of WeChat Mini Program Interface