Downloads · 30 days
7
22% of all-time downloads
marian_tig_eng
yfterelu/marian_tig_eng
marian_tig_eng is a machine learning model from yfterelu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
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.
All-time downloads
32
Public
Parameters
77.1M
926 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors617 MB · 50%
At a glance
- License
- apache-2.0
- Model type
- marian
- Access
- Public
- Created
- Aug 13, 2025
- Updated
- Aug 14, 2025
- SHA
- 73a19a1c
Model card
From the Hugging Face model README
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))
- Type
- marian
- License
- apache-2.0
- Languages
- ti, en
- Created
- Aug 13, 2025
- Updated
- Aug 14, 2025