🎮 Real-time game subtitle translator with AI-powered OCR. Context-aware translation for 20+ languages. Free offline models + dirt cheap APIs. Perfect for gaming in foreign languages!

translate your prompt text to enlish using local translation models

https://translate.smc.org.in/

Few NLP augmentation techniques: synonym/antonym and back translation.

Links to my repositories, where I implement a wide variety of Natural Language Processing models using TensorFlow and Hugging Face.

Hybrid RAG system for translating Ancient Egyptian transliterations using the TLA dataset.

This AI-powered MVP (Minimum Viable Product) is designed to help users enhance their English-speaking skills through real-time, personalized feedback in Marathi.

A real-time Speech-to-Speech translation pipeline (ASR ➡️ NMT ➡️ TTS) using OpenAI Whisper, MarianMT, and gTTS. Features a Flask backend and a responsive web UI for low-latency multilingual communication and audio synthesis.

🎮 Real-time game subtitle translator with AI-powered OCR. Context-aware translation for 20+ languages. Free offline models + dirt cheap APIs. Perfect for gaming in foreign languages!

This project is a AI tool translator using NLP techniques

Python and C++ implementations of MarianMT that run on the Rockchip NPU

Persona Styled Recipes are generated given a list of ingredients

NLP course project: Comparison of mBART-50 and Helsinki-NLP MarianMT models for Polish–Croatian machine translation with BLEU evaluation

A project for the comparative analysis of NMT architectures (Seq2Seq LSTM, MarianMT, M2M100), evaluating accuracy, adaptability, noise robustness and potential improvements.

Fine-tuning Helsinki-NLP/opus-mt-en-de on WMT24 for English to German NMT | SacreBLEU 32.22 | MarianMT Transformer

A finetuned MarianMT EN2ZH model for usage in the domain of Aviation Communication

A multi-language translator built using pre-trained MarianMT models from HuggingFace. It supports English-to-French, Hindi, Russian, and Spanish translation with BLEU score evaluation to assess translation quality. Ideal for real-time translation and NLP experimentation.

Encoder-Decoder NLP model with Beam Search and MarianMT for sequence-to-sequence tasks. Includes a web UI frontend and Flask/Streamlit backend.

Encoder-Decoder NLP model with Beam Search and MarianMT for sequence-to-sequence tasks. Includes a web UI frontend and Flask/Streamlit backend.