summarization

This repo provides sample generative AI stacks built atop the AWS Generative AI CDK Constructs.

Abstractive Text Summarization using Transformer

Bringing Generative AI to the way the Civil Service works

VLM driven tool that processes surveillance videos, extracts frames, and generates insightful annotations using a fine-tuned Florence-2 Vision-Language Model. Includes a Gradio-based interface for querying and analyzing video footage.

CLI & Python API to easily summarize text-based files with transformers

Summarize web pages and YouTube videos with pluggable LLM backends (Ollama, OpenAI). CLI, library, and Gradio UI.

AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while preserving semantic meaning with advanced compression strategies.

The official implementation of 'Align and Attend: Multimodal Summarization with Dual Contrastive Losses' (CVPR 2023)

A tool to automatically summarize documents abstractively using the BART or PreSumm Machine Learning Model.

Unofficial (Golang) Go bindings for the Hugging Face Inference API

Turn speech into semantic paragraphs in real time, on a CPU (no GPU) — single-pass streaming chunker + Moonshine STT + a live mic demo. Plus a transcribe/chunk/summarize API.

A sophisticated RAG (Retrieval-Augmented Generation) Telegram bot that transforms articles and documents into interactive knowledge bases. Upload PDFs/URLs and get AI-powered answers with source citations.

Experiments with Hugging Face 🔬 🤗

A collection of atomic notes summarizing Telegram posts from the AI Projects. All content is in Russian.

The first large-scale summarization corpus for the Indonesian language. AACL 2020.

[TACL, EMNLP 2025 Oral] Code, datasets, and checkpoints for the paper "CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation"

Summarization, topic generation using GPT3

Claude Code skill: summarize videos, audio & podcasts with local cached transcription

A tool for summarizing search results and website content using FAISS, LLMs, and the Retrieval-Augmented Generation (RAG) technique.

A Bert2Bert model which able to summarize articles!