🇮🇳 Assamese → English Translation Model

This model is a fine-tuned version of Helsinki-NLP/opus-mt-mul-en on a custom Assamese–English parallel dataset. It translates Assamese text into English.

🧠 Model Details

• Base model: Helsinki-NLP/opus-mt-mul-en
• Framework: 🤗 Transformers (PyTorch)
• Fine-tuning epochs: 8
• Learning rate: 3e-5
• Max sequence length: 128

💬 Example Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_name = 'Sazid2/assamese-english-translator'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

text = 'মই এজন শিক্ষক।'
inputs = tokenizer(text, return_tensors='pt')
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Output:

I am a teacher.

⚙️ Intended Use

• Educational and research purposes
• Assamese ↔ English translation applications

⚠️ Limitations

The model may produce literal or inaccurate translations for complex, idiomatic, or poetic Assamese expressions.