Hadryan's repositories
Audio-Deepfake-Detection
Audio Deepfake Detection is a web application that utilizes machine learning techniques to analyze audio files and determine if they are real or generated by deepfake algorithms. It features user registration, audio file upload, audio feature extraction, comparison with a pre-defined dataset, and classification of audio as real or deepfake.
audio2photoreal
Code and dataset for photorealistic Codec Avatars driven from audio
CogVideo
Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
DailyHotApi
🔥 今日热榜 API，一个聚合热门数据的 API 接口，支持 RSS 模式 及 Vercel 部署 | 前端页面：https://github.com/imsyy/DailyHot
DailyHotApi-Vercel
🔥 今日热榜 API - 一个聚合热门数据的 API 接口 - Vercel 快速部署
Deep-Live-Cam
real time face swap and one-click video deepfake with only a single image (uncensored)
DEP-Former
DEP-Former: Multimodal Depression Recognition Based on Facial Expressions and Audio Features via Emotional Changes
drivestudio
A 3DGS framework for omni urban scene reconstruction and simulation.
EasySpider
A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。
Genre-Classifier
A simple neural network project that allows you to classify music audio files by genre, based on different acoustic features. Data was gathered from the "Music Features" dataset available on Kaggle.
instagram-api2
Simple PHP Private API that allows you to use both mobile and web APIs of Instagram
InstagramTheftyScraperPosterHuman
InstagramTheftyScraperPosterHuman is an advanced tool for automating the process of scraping, uploading, and managing Instagram reels. This tool builds upon previous versions, introducing several enhancements and new functionalities to improve automation, human-like interactions, and bot detection prevention.
keypoint_promptable_reidentification
[ECCV24] Keypoint Promptable Re-Identification: SOTA ReID method robust to occlusions and multi-person ambiguity
make-a-video-pytorch
Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch
MiniCPM-V
MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
Music-Recognition-and-Recommendation-System1
“ Waves “ is a music recognition and recommendation system inspired by shazam .The system recognizes a 10 seconds recorded music by generating unique fingerprints using Fast Fourier Transform Algorithm . This system not only provides convenient song identification but also generates music recommendations based on audio features .
podcastr-ai_app_next
Podcastr is an AI SaaS platform, built on Next.js, that enables users to create podcasts with advanced features like text-to-audio conversion, thumbnail Image generation and seamless playback.
Sangeet_Guru
Sangeet Guru: A music generation app where users input a music style description to get custom audio tracks. Features a clean interface with a small logo, example prompts, and a button to generate music. Built with FastAPI for the backend and Streamlit for the frontend.
sapiens
High-resolution models for human tasks.
sayaslicer
Cross-platform audio slicer with BMS-related features
segment-anything-2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
simple_emotion_detection
This project focuses on emotion detection using audio features and Dynamic Time Warping (DTW) distance metrics. It involves comparing the efficiency of classical DTW and FastDTW in terms of speed, accuracy, and scalability. The project includes data preparation, model development, and performance analysis.
SongYearReleasePrediction
Parallel processing to analyze audio features, predict song release years, and create visualizations
Sounds-Classification
This project implements an audio classification system that can categorize sound files into predefined classes. It uses signal processing techniques to preprocess audio data, extracts relevant acoustic features, and employs a Random Forest classifier for the classification task.
Spotify-Python
This project focuses on analyzing Spotify's music data to extract insights related to songs, audio features, and user preferences using Python. By leveraging libraries such as Pandas, NumPy, Matplotlib, and Seaborn, the project aims to visualize trends and patterns, ultimately enhancing understanding of the music streaming landscape.
spotube
🎧 Open source Spotify client that doesn't require Premium nor uses Electron! Available for both desktop & mobile!
taipy
Turns Data and AI algorithms into production-ready web applications in no time.
telegram-configs-collector
The Script Gathers Juicity, Hysteria, Tuic, Vless, Vmess, Trojan, and Shadowsocks Configurations From Telegram Channels and Subscription Links