Krupa22/hindi-slang-model

Hindi to English Translation Model

This repository contains a pre-trained machine translation model for translating text from Hindi to English. The model is based on the Helsinki-NLP/opus-mt-hi-en model, utilizing the Transformers framework.

Model Details

• Model Name: Helsinki-NLP/opus-mt-hi-en
• Language: Hindi to English
• Framework: Transformers (Hugging Face)
• License: Apache 2.0

Installation

To use this model, install the required dependencies:

pip install transformers torch

Usage

You can use this model with the Hugging Face transformers library as follows:

from transformers import MarianMTModel, MarianTokenizer

def translate(text):
    model_name = "Helsinki-NLP/opus-mt-hi-en"
    tokenizer = MarianTokenizer.from_pretrained(model_name)
    model = MarianMTModel.from_pretrained(model_name)
    
    # Tokenize input text
    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
    
    # Generate translation
    translated_tokens = model.generate(**inputs)
    translation = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)
    
    return translation[0]

# Example usage
hindi_text = "\u092e\u0947\u0930\u093e \u0928\u093e\u092e \u0930\u093e\u0939\u0941\u0932 \u0939\u0948"
english_translation = translate(hindi_text)
print("Translation:", english_translation)

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for more details.

Acknowledgments

• Helsinki-NLP for providing the OPUS-MT model.
• Hugging Face for the transformers library.