---
title: NLLB-200 Turkmen English Translation
emoji: 🌐
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.31.0
app_file: app.py
pinned: false
license: cc-by-nc-4.0
models:
  - XSkills/nllb-200-turkmen-english-lora
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
---

# NLLB-200 Turkmen-English Translation Demo

This Space provides an interactive demo for the NLLB-200 (600M) model fine-tuned for Turkmen-English translation using LoRA. You can read all the deails about the model at the [Medium article](https://medium.com/@merdand/)

## Features
- Bidirectional translation (Turkmen ↔ English)
- Clean and simple interface
- Example translations provided
- Performance metrics displayed

## Model Information
- Base model: facebook/nllb-200-distilled-600M
- Fine-tuning method: LoRA on q_proj & v_proj matrices
- Model: [nllb-200-turkmen-english-lora](https://huggingface.co/XSkills/nllb-200-turkmen-english-lora)
- Model repository: [GitHub](https://github.com/merdandt/nllb-tk-en-lora)
- Training data: [turkmen_english_s500](https://huggingface.co/datasets/XSkills/turkmen_english_s500) 600 parallel sentences
- License: CC-BY-NC 4.0

Created by Merdan Durdyyev