Marian Tigrigna → English Translation

This is a fine-tuned MarianMT model for translating from Tigrigna (ti) to English (en).
It was trained using a custom dataset prepared in Google Colab.

Download the Training Dataset

The full dataset used for fine-tuning is available here.

Example Usage

Example Python code:

from transformers import MarianTokenizer, MarianMTModel
model_name = "yfterelu/marian_tig_eng"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)

text = "ፅቡቕ ጅማሮ ይግበረልካ/ኪ።"
inputs = tokenizer(text, return_tensors="pt")
translated_tokens = model.generate(**inputs)
print(tokenizer.decode(translated_tokens[0], skip_special_tokens=True))