Pinned Repositories
AT4ChineseNER
Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism
autolabel
Label, clean and enrich text datasets with LLMs.
Awesome-Chinese-NLP
A curated list of resources for Chinese NLP 中文自然语言处理相关资料
BERT-NER-Pytorch
Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)
bertviz
Tool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.)
BiLSTM-LAN
Hierarchically-Refined Label Attention Network for Sequence Labeling
brat-docker
containerised brat (http://brat.nlplab.org/)
CycleGAN_Pytorch
用于图片风格迁移的生成式对抗网络
OpenCLaP
Open Chinese Language Pre-trained Model Zoo
PyTorch-Bert-BiLSTM-ATT-LJP
PyTorch-Bert-BiLSTM-ATT-LJP
lichunnan's Repositories
lichunnan/autolabel
Label, clean and enrich text datasets with LLMs.
lichunnan/Chatbot_CN
基于金融-司法领域(兼有闲聊性质)的聊天机器人，其中的主要模块有信息抽取、NLU、NLG、知识图谱等，并且利用Django整合了前端展示,目前已经封装了nlp和kg的restful接口
lichunnan/chatgpt-on-wechat
基于大模型搭建的微信聊天机器人，同时支持微信、企业微信、公众号、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/GLM-4/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。
lichunnan/convo
Open source voice bot for Humanoid Robots and virtual digital humans
lichunnan/deepin-wine
【deepin源移植】Debian/Ubuntu上的QQ/微信快速安装方式
lichunnan/docker-aio
Docker 安装镜像一条龙 All In One
lichunnan/DockerTarBuilder
它是一个工作流。可快速构建指定架构/平台的docker镜像
lichunnan/duckling
Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.
lichunnan/KBQA-for-Diagnosis
Knowledge Graph,Question Answering System，基于知识图谱和向量检索的医疗诊断问答系统
lichunnan/langchain-ChatGLM
langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识的 ChatGLM 问答
lichunnan/larynx2
A fast, local neural text to speech system
lichunnan/MarkTool
这是一款基于web、面向领域的通用文本标注工具，支持大规模实体标注、关系标注、事件标注、文本分类、基于字典匹配和正则匹配的自动标注以及用于实现归一化的标准名标注，同时也支持文本的迭代标注和实体的嵌套标注。标注规范可自定义且同类型任务中可“一次创建多次复用”。通过分级实体集合扩大了实体类型的规模，并设计了全新高效的标注方式，提升了用户体验和标注效率。此外，本工具增加了审核环节，可对多人的标注结果进行一致性检验、自动合并和手动调整，提高了标注结果的准确率。
lichunnan/MB-iSTFT-VITS
Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform
lichunnan/mediapipe-Fitness-counter
Fitness counter/pull-up counter/squat counter/push-up counter based on mediapipe and KNN classification algorithm.基于mediapipe和KNN分类算法的健身计数器/引体向上计数器/深蹲计数器/俯卧撑计数器。
lichunnan/MLRC2020-EmbedKGQA
This is the code for the MLRC2020 challenge w.r.t. the ACL 2020 paper Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings
lichunnan/mm-cot
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
lichunnan/Modern_GUI_PyDracula_PySide6_or_PyQt6
lichunnan/mrc-for-flat-nested-ner
Code for ACL 2020 paper `A Unified MRC Framework for Named Entity Recognition`
lichunnan/NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
lichunnan/openpose
用于实时检测的一个项目
lichunnan/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.
lichunnan/QA-Survey
北航大数据高精尖中心研究张日崇团队对问答系统的总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TabletQA）和基于视觉的问答系统（VisualQA），每类系统分别对学术界和工业界进行总结。
lichunnan/QASystemOnMedicalKG
A tutorial and implement of disease centered Medical knowledge graph and qa system based on it。知识图谱构建，自动问答，基于kg的自动问答。以疾病为中心的一定规模医药领域知识图谱，并以该知识图谱完成自动问答与分析服务。
lichunnan/rasa_bot_front
基于 rasa 的机器人的前端项目
lichunnan/streamlit-elements
Create a draggable and resizable dashboard in Streamlit, featuring Material UI widgets, Monaco editor (Visual Studio Code), Nivo charts, and more!
lichunnan/task-chatbot-sample-using-RASA
rasa是一个机器学习框架，专门用于快速构建对话系统。本仓库用rasa3.0版本构建了了一个订机票的对话机器人demo。
lichunnan/trl
Train transformer language models with reinforcement learning.
lichunnan/VITS-BigVGAN-SpanPSP-Chinese
基于PyTorch的VITS-BigVGAN的tts中文模型，加入韵律预测模型。
lichunnan/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
lichunnan/Whisper-Input
可以实现按下 Option 按钮开始录制，抬起按钮就结束录制，并调用 Groq Whisper Large V3 Turbo 模型进行转译，由于 Groq 的速度非常快，所以大部分的语音输入都可以在 1-2s 内反馈。并且得益于 whisper 的强大能力，转译效果非常不错。