Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
Repository Index
60,121 visible repositories in the index
1–14 of 14 · Most stars
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
- code-generation
- pretrained-models
- tools
PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.
All-in-One Development Tool based on PaddlePaddle
- classification
- segmentation
- deployment
- ocr
README file generator, powered by AI.
- readme-generator
- readme
- readme-md-generator
- ai
An open-source read-along document reader server with high-quality TTS options, synchronized highlighting, and audiobook export for EPUB, PDF, DOCX, TXT, and MD.
- kokoro-tts
- openai-api
- text-to-speech
WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.
:grey_question: Visual Question Answering in Torch
Python package implementing ML feature engineering and pre-processing for polars or pandas dataframes.
- feature-engineering
- transformers
- pre-processing
- data-science
Push-to-talk voice dictation for Linux. 100% local, multilingual (25+ languages), with speaker diarization. Qt frontend, Rust backend on NVIDIA Parakeet via ONNX Runtime. KDE Plasmoid integrated.
- asr
- linux
- nvidia
- parakeet
Tagify produces a set of tags from a given source. Source can be either an HTML page, a Markdown document or a plain text. Supports English, Russian, Chinese, Hindi, Spanish, Arabic, Japanese, German, Hebrew, French and Korean languages.
- tagify
- keywords
- keyword-extraction
- html
Turn any Java, Kotlin or Python project into an AI-ready context file in one command.