#
Starred repositories
Memory for AI Agents; SOTA in AI Agent Memory; Announcing OpenMemory MCP - local and secure memory management.
TAG-Bench: A benchmark for table-augmented generation (TAG)
🚀 智谱清言ChatGLM-4-Plus大模型逆向API【特长：超强智能体】，支持高速流式输出、支持智能体对话、支持多轮对话、支持沉思模型、支持Zero思考推理模型、支持视频生成、支持AI绘图、支持联网搜索、支持长文档解读、支持代码调用、支持图像解析，零配置部署，多路token支持，自动清理会话痕迹，仅供测试，如需商用请前往官方开放平台。
ChatGPT Java SDK支持流式输出、Gpt插件、联网。支持OpenAI官方所有接口。ChatGPT的Java客户端。OpenAI GPT-3.5-Turb GPT-4 Api Client for Java
Superfast AI decision making and intelligent processing of multi-modal data.
langchain学习笔记，包含langchain源码解读、langchain中使用中文模型、langchain实例等。
🦜🔗 Build context-aware reasoning applications
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…
huqianghui / Azure-Cognitive-Search-Azure-OpenAI-Accelerator
Forked from MSUSAzureAccelerators/Azure-Cognitive-Search-Azure-OpenAI-AcceleratorVirtual Assistant - GPT Smart Search Engine - Bot Framework + Azure OpenAI + Azure Search + Azure SQL + Azure Document Intelligence + LangChain + CosmosDB
优质稳定的OpenAI的API接口-For企业和开发者。OpenAI的api proxy，支持ChatGPT的API调用，支持openai的API接口，支持：gpt-4，gpt-3.5。不需要openai Key, 不需要买openai的账号，不需要美元的银行卡，通通不用的，直接调用就行，稳定好用！！智增增
Demo programs for the Talking Head Anime from a Single Image 2: More Expressive project.
Easily export the Genshin Impact wish record.
Implements PLDA score computation using pretrained PLDA model for speaker diarization
PyTorch implementation of PLDA as described in https://ravisoji.com/assets/papers/ioffe2006probabilistic.pdf
Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)
Supervised Machine Learning Model for Accent Recognition in English Speech using Sequential MFCC Features
WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation, and training audio classification models with PyTorch backend.
Perform force alignment on Mandarin data using aidatatang pretrained model at https://kaldi-asr.org/models/m10
中文语音识别系列，读者可以借助它快速训练属于自己的中文语音识别模型，或直接使用预训练模型测试效果。
Character based Temporal Convolutional Networks + Attention Layer
An Open Source Tools for Speaker Recognition
Exploring use of deep learning in signal processing
CNN+BiLSTM+Attention Multivariate Time Series Prediction implemented by Keras
Implementing speaker recognition using Python (GMM-UBM)