Hugging Face's logo

Spaces:
RohanAi
/
Quantized_lang._Translator
Sleeping

App Files Community
Quantized_lang._Translator / README.md
RohanAi's picture
RohanAi
Upload folder using huggingface_hub
50eb13f verified
preview code
|
raw
history blame contribute delete
1.2 kB

A newer version of the Gradio SDK is available: 6.5.1

Upgrade
metadata 
title: Quantized_lang._Translator
app_file: app.py
sdk: gradio
sdk_version: 5.48.0

NLLB-FB Language Translator (Quantized, CPU-Friendly)

This project provides a quantized, CPU-optimized version of the NLLB (No Language Left Behind) Facebook language translation model. It enables very fast inference on CPUs for translating between a wide variety of languages.

Features

  • Quantized Model: Reduced model size for efficient CPU usage.
  • Fast Inference: Optimized for low-latency translation on standard CPUs.
  • Multi-language Support: Translate between many language pairs.
  • Easy Integration: Simple API for batch and single-sentence translation.

Usage

  1. Install dependencies:

    pip install torch transformers

  2. Run the Gradio app:

    python app.py

Supported Languages

See the NLLB-200 language list for all supported languages.

References