Lists (21)
Starred repositories
35
stars
written in Python
Clear filter
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
LlamaIndex is the leading framework for building LLM-powered agents over your data.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
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…
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)
视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.
pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。
📄 Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVINO, PaddlePaddle and PyTorch.
Production First and Production Ready End-to-End Speech Recognition Toolkit
A synthetic data generator for text recognition
A dark style sheet for QtWidgets application
[python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning
Unsupervised Word Segmentation for Neural Machine Translation and Text Generation
[ECCV 2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.
make a better chinese character recognition OCR than tesseract
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
基于深度学习的漫画翻译辅助工具，包含翻译、朗读、图像去字、自动嵌字功能。 目的是帮助非专业汉化人员完成更简单，快速的翻译任务。
Arch Linux CN Community repo mirrors list
Library for translating between 200 languages. Built on 🤗 transformers.