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.

VideoChat 是一款智能音视频内容解读助手，支持批量上传音视频文件并自动转录为文字。通过 AI 技术，它能快速生成内容总结、详细解读和思维导图，并提供智能对话功能，帮助用户更高效地理解和分析音视频内容。支持多种格式导出字幕文件。

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.

TikMatrix is a professional TikTok matrix software designed for operators. It controls multiple Android phones via a computer for automatic registration, login, account nurturing, messaging, and po…

Up to 10x faster strings for C, C++, Python, Rust, and Swift, leveraging NEON, AVX2, AVX-512, and SWAR to accelerate search, sort, edit distances, alignment scores, etc 🦖

🚀「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。

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

Original implementation of "3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes"

🚀 你的YOLO部署神器。TensorRT Plugin、CUDA Kernel、CUDA Graphs三管齐下，享受闪电般的推理速度。| Your YOLO Deployment Powerhouse. With the synergy of TensorRT Plugins, CUDA Kernels, and CUDA Graphs, experience lightning-fast…

该工具用于导出正在运行中的微信进程的 key 并自动解密所有微信数据库文件以及导出 key 后数据库文件离线解密。

21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

DSPy: The framework for programming—not prompting—foundation models

deploy whsiper on aws

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

跨平台的视频结构化（视频分析）框架，觉得有帮助的请给个星星：）。

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Firefly: 大模型训练工具，支持训练Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型