nllb200

Easy-Translate is a script for translating large text files with a SINGLE COMMAND. Easy-Translate is designed to be as easy as possible for beginners and as seamlesscustomizable and as possible for advanced users.

A performant high-throughput CPU-based API for Meta's No Language Left Behind (NLLB) using CTranslate2, hosted on Hugging Face Spaces.

This project use the Meta NLLB-200 translation model through the Hugging Face transformers library.

nllb-200 distilled 350M for English to Korean translation

Multi-engine neural translator across 200 languages — local NLLB-200 / MADLAD / Ollama + free Gemini/Groq APIs. FastAPI + Next.js.

Example application for the task of fine-tuning pretrained machine translation models on highly domain-specific, self-extracted translated sentences

Crash course on LangChain for LLM Application Developement by DeepLearningAI

Translator demo app built with Transformers.js + Tamagui + Next.js

nlingua2 – Command-line tool for transcribing and translating .srt subtitles using offline AI models (OpenAI Whisper + Meta NLLB).

A implementation of Meta's NLLB translator, modified to run on Apple Silicon Macs (M1–M4) using GPU acceleration via PyTorch MPS. No CUDA or quantization required. Fast, offline language translation with Gradio UI. This is part of our AI Ethics coursework and paper.

Repository of our paper Nesciun Lengaz Lascià Endò: Machine Translation for Fassa Ladin.

THOTH Language Translator is a powerful, privacy-first, state-of-the art translation tool that runs offline. It uses the NLLB-200 engine to translate over 200 languages, with option to switch to an alternate translation engine, Argos.

Transformo Doc

A telegram bot for text, voice, and image translation using NLLB and dl-translate

This project is a Flask-based web application that translates text from one language to another using a pre-trained machine translation model (NLLB-200). The application provides a user-friendly interface for selecting languages and entering text, and it returns the translated output along with the computation time.

Comparing mBART-50, NLLB-200, Helsinki-NLP & mT5 for English→Malayalam NMT using Back-Translation data augmentation in low-resource settings.

This repository contains Python implementations for processing multilingual text data, focusing on language classification and translation tasks. The project addresses two distinct tasks: language classification and English translation, each involving different complexities in the processing of text data.

An offline-first, NLP-driven disease surveillance system that automates the extraction, analysis, and translation of unstructured epidemiological reports. Utilizing rule-based NLP, WordNet, and NLLB-200, it identifies outbreak severity, translates intelligence into regional Indian languages, and plots real-time alerts on an interactive Leaflet map.