Official PyTorch implementation of Extract Free Dense Misalignment from CLIP (AAAI'25)
-
Updated
Apr 20, 2025 - Python
Official PyTorch implementation of Extract Free Dense Misalignment from CLIP (AAAI'25)
🧠 A flexible machine & deep learning framework built from scratch using only NumPy
predicting Protein Subcellular Localization from quantitative label-free imaging with phase and polarization
Developed a Marathi speech-to-text application using the Hugging Face whisper ASR models. Trained the model with a custom audio dataset and fine-tuned it for optimized performance. Deployed the model on the Hugging Face Model Hub, achieving a WER of 0.74 for the base model.
🏞 A content-based image retrieval (CBIR) system
Adaptive generalized review summarization system using optimized transformers.
Embedding analysis and some insights on the GPT-2 architecture
FeelBack es un proyecto personal que consite en una aplicación web simple tipo chat construida con Flask y un modelo de HuggingFace que permite a los usuarios analizar el sentimiento de textos en tiempo real.
💳 Detect fraudulent payment transactions with this transformer-based system, leveraging LoRA for efficient fine-tuning and providing real-time predictions.
This repo contains lecture notes and assignments of stanford's CS224N course of NLP
Analyze the emotional tone of any text using AI and Transformers.
solution for assessment at https://docs.google.com/forms/d/e/1FAIpQLSf4mqNST9kC6P41EDtaEYk65k0DptjuSyA_iRBoN10FwalSpw/viewform
Language Generator Model. Can "Miguel de Cervantes" be digitally reincarnated?
Analyse automatique des réponses à des formulaires numériques. Transforme des questions et réponses ouvertes en insights exploitables grâce à l’IA. Inclut détection d’objectif, résumé automatique et chatbot interactif.
mengkelompokan gambar bedasarkan kemiripan pada sebuah gambar
NLP pipeline using Hugging Face transformers, fine-tuned for text tasks. Containerized with Docker
LinkedIn ChatBot (Pre-ChatGPT Era): An early, low-resource solution for automating LinkedIn interactions. This project combines web scraping, translation services, and a conversational AI model for automated responses. Please use responsibly, considering LinkedIn's terms of service.
Attempt at the Amazon ML Challenge 2024
An AI-powered Document Summarization System built with Streamlit and Python. It features an Extractive Track using statistical heuristics (TF-IDF/Frequency vectors) and an Abstractive Track utilizing deep learning (NLP Transformers) to process and synthesize long text documents efficiently. Created as part of the TEYZIX CORE Internship Program....
AI-powered story generator that creates intricate stories based on initial snippets given by users.
Add a description, image, and links to the trasnformers topic page so that developers can more easily learn about it.
To associate your repository with the trasnformers topic, visit your repo's landing page and select "manage topics."