DWHNicholas

Pinned Repositories

ai-research-keyphrase-extraction
EmbedRank: Unsupervised Keyphrase Extraction using Sentence Embeddings (official implementation)
Language:Python00
aliendao
huggingface mirror download
Language:Python00
baidu_crawel
通过python爬虫实现对百度图片的批量下载
Language:Python00
bcut-asr
使用必剪API的语音字幕识别
Language:Python00
Bert-Chinese-Text-Classification-Pytorch
使用Bert，ERNIE，进行中文文本分类
Language:Python00
bert_crf_sequence_annotation
基于Pytorch+BERT+CRF的NLP序列标注模型，目前包括分词，词性标注，命名实体识别等
Language:Python00
BERT_implement
使用BERT模型进行文本分类，相似句子判断，以及词性标注
Language:Python00
bert_seq2seq
pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。
Language:Python0 0 00
bi-lstm-crf
使用keras实现的基于Bi-LSTM + CRF的中文分词+词性标注
Language:Python00
ChatGPT-Web
使用GPT-3.5 API创建的ChatGPT聊天页面，支持云部署，多用户使用，多对话管理，公式显示，流式动态显示，windows和linux均可极简部署，网页版 html python flask
Language:Python00

DWHNicholas's Repositories

DWHNicholas/ImageNet_chinese_cls
ImageNet，由于有1000类，但是很多我们都是不需要使用的，而且国内大部分需要中文，他的英文非常没有辨识度，且很多重复的，创建一个分类标识
11
DWHNicholas/CLIP4Clip
An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"
DWHNicholas/Crawl_Douyin_video
这是一个根据抖音视频id保存视频至本地的爬虫项目，可以批量爬取抖音视频，项目依托scrapy框架及selenium自动化技术
DWHNicholas/douyin
抖音爬虫——采集账号主页、喜欢、收藏、音乐原声、话题、搜索、合集、作品、关注、粉丝等公开数据。
DWHNicholas/Douyin_TikTok_Download_API
🚀「Douyin_TikTok_Download_API」是一个开箱即用的高性能异步抖音、快手、TikTok、Bilibili数据爬取工具，支持API调用，在线批量解析及下载。
DWHNicholas/fish-speech
Brand new TTS solution
DWHNicholas/gpt4free
The official gpt4free repository | various collection of powerful language models
DWHNicholas/Grounded-Segment-Anything
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
DWHNicholas/Image-Downloader
Download images from Google, Bing, Baidu. 谷歌、百度、必应图片下载.
DWHNicholas/image-textualization
Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions
DWHNicholas/lora-
lora分析研究流程
Language:Python
DWHNicholas/MediaCrawler
小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频｜评论爬虫、微博帖子｜评论爬虫、百度贴吧帖子｜百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫
DWHNicholas/MiniCPM-V
MiniCPM-V 2.0: An Efficient End-side MLLM with Strong OCR and Understanding Capabilities
DWHNicholas/MoneyPrinterTurbo
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
DWHNicholas/Moore-AnimateAnyone
Character Animation (AnimateAnyone, Face Reenactment)
DWHNicholas/MS-Diffusion
Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
DWHNicholas/OnnxOCR
基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快
DWHNicholas/openai-cookbook
Examples and guides for using the OpenAI API
DWHNicholas/PaddleOCRFastAPI
A simple way to deploy PaddleOCR based on FastAPI. (PaddleOCR 的 FastAPI 快速部署方案)
DWHNicholas/Picf
Picf 是一款智能相册，具有人脸识别分类、人脸搜索、相似图片筛查等功能。 Picf is a smart photo album, which can classify images by face, search images with same face as well as find similar images.
DWHNicholas/ProPainter
[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting
DWHNicholas/pyhanlp
中文分词
DWHNicholas/SenseVoice
Multilingual Voice Understanding Model
DWHNicholas/sherpa-onnx
Speech-to-text, text-to-speech, and speaker recognition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift, Dart, JavaScript, Flutter
DWHNicholas/shotcut
cross-platform (Qt), open-source (GPLv3) video editor
DWHNicholas/StoryMaker
StoryMaker: Towards consistent characters in text-to-image generation
DWHNicholas/TinyAgent
基于ReAct手搓一个Agent Demo
DWHNicholas/Tutorial
LLM Tutorial
DWHNicholas/xhs
基于小红书 Web 端进行的请求封装。https://reajason.github.io/xhs/
DWHNicholas/XHS-Downloader
小红书链接提取/作品采集工具：提取账号发布、收藏、点赞作品链接；提取搜索结果作品、用户链接；采集小红书作品信息；提取小红书作品下载地址；下载小红书无水印作品文件！