Spaces:

TGPro1
/

NLLB200

Sleeping

App Files Files Community

NLLB200 / README.md

TGPro1

Deploy NLLB-200 Translation API with Gradio

c4f4c46 about 1 month ago

preview code

raw

history blame contribute delete

2.11 kB

A newer version of the Gradio SDK is available: 6.6.0

Upgrade

metadata

title: NLLB200
emoji: 🌍
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: apache-2.0

NLLB-200 Translation API

High-quality translation API powered by Meta's No Language Left Behind (NLLB-200) model.

Features

✅ 200 Languages Supported - Direct translation between any language pair
✅ 44% Better Quality - Compared to previous translation models
✅ +70% for Complex Languages - Especially Arabic, Hindi, and other low-resource languages
✅ No Pivot Translation - Direct translation without going through English
✅ Cached Results - Faster repeated translations
✅ API Access - Use via Gradio Client or HTTP

Supported Languages (Sample)

Arabic, English, French, Spanish, German, Italian, Portuguese, Russian, Japanese, Korean, Chinese, Hindi, Turkish, Dutch, Polish, Swedish, Indonesian, Vietnamese, Thai, Ukrainian, Romanian, Greek, Hebrew, and more!

Usage

Web Interface

Visit the Space and use the interactive interface to translate text between any supported languages.

API

from gradio_client import Client

client = Client("TGPro1/NLLB200")
result = client.predict(
    "Hello, world!",  # text
    "English",         # source language
    "Arabic",          # target language
    api_name="/predict"
)
print(result)  # مرحبا بالعالم!

Model

Model: facebook/nllb-200-distilled-600M
Parameters: 600M
Size: ~2.4GB
Languages: 200

Performance

Quality: State-of-the-art for low-resource languages
Speed: Fast inference with distilled model
Cache: LRU cache for frequently translated phrases

Credits

Model: Meta AI Research - NLLB Project
Benchmark: FLORES-200
License: Apache 2.0