Views
No views yet
| Metric | Value |
|---|---|
| Sentences | 153,341 |
| Tokens | 2,410,758 |
| Unique words | 194,469 |
| Parameter | Value |
|---|---|
| Algorithm | Skip-gram |
| Dimension | 100 |
| Epochs | 20 |
| Window size | 5 |
| Character n-grams | 3–6 |
1import fasttext
2
3model = fasttext.load_model("awngi_fasttext_skipgram.bin")
4
5vector = model.get_word_vector("አውጚ")
6
7print(vector[:10])
8Intended Use
9
10This model is designed for:
11
12Named Entity Recognition
13Low-resource NLP
14Ethiopian language processing
15Morphologically rich language representation
16Citation
17@article{andualem2026awnginer,
18 title={AwngiNER: A Benchmark Dataset and fastText-Enhanced Neural Models for Named Entity Recognition in Awngi},
19 author={Andualem, Amogne},
20 year={2026}
21}