|
|
---
|
|
|
language:
|
|
|
- en
|
|
|
- te
|
|
|
tags:
|
|
|
- translation
|
|
|
- machine-translation
|
|
|
- NLP
|
|
|
- pytorch
|
|
|
license: "cc-by-4.0"
|
|
|
datasets:
|
|
|
- hima06varshini/english-telugu-parallel-corpus
|
|
|
widget:
|
|
|
- text: "Translate this sentence from English to Telugu"
|
|
|
---
|
|
|
# **English-to-Telugu Translation Model** 🏆
|
|
|
|
|
|
## **📌 Model Overview**
|
|
|
This is a **Neural Machine Translation (NMT) model** trained to translate English sentences into Telugu using **Transformer-based architectures**.
|
|
|
|
|
|
- ✅ **Handles complex sentence structures**
|
|
|
- ✅ **Supports general & conversational language**
|
|
|
- ✅ **Fine-tuned on English-Telugu parallel corpora**
|
|
|
|
|
|
---
|
|
|
|
|
|
## **📖 How to Use the Model**
|
|
|
You can load this model using **Hugging Face Transformers**:
|
|
|
|
|
|
```python
|
|
|
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
|
|
|
|
|
model_name = "hima06varshini/english-to-telugu-translation"
|
|
|
token = "YOUR_ACCESS_TOKEN" # Replace with your Hugging Face token if required
|
|
|
|
|
|
# Load Model & Tokenizer
|
|
|
model = AutoModelForSeq2SeqLM.from_pretrained(model_name, token=token)
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name, token=token)
|
|
|
|
|
|
def translate(text):
|
|
|
inputs = tokenizer(text, return_tensors="pt")
|
|
|
outputs = model.generate(**inputs)
|
|
|
return tokenizer.decode(outputs[0], skip_special_tokens=True)
|
|
|
|
|
|
# Example Translation
|
|
|
text = "Hello, how are you?"
|
|
|
print(translate(text)) |
