Create README.md

README.md

@@ -0,0 +1,47 @@
+---
+license: cc
+language:
+- ga
+- mga
+pipeline_tag: feature-extraction
+---
+
+### Training Data
+
+The models were trained on Middle Irish texts from [CELT](https://celt.ucc.ie/publishd.html). A text was included in the training dataset if "Middle Irish" or the dates "900-1200" were explicitely mentioned in its metadata on CELT, including texts marked as "Old and Middle Irish" or "Old, Middle and Early Modern Irish". Therefore, Middle Irish models can contain some Old and Early Modern Irish words.
+
+### Available Models
+
+There are 3 models in this familily:
+
+- **Cased**: `middle_irish_cased_ft_100_5_2.txt`
+- **Lowercase**: `middle_irish_lower_ft_100_5_2.txt`
+- **Lowercase with initial mutations removed**: `middle_irish_lower_demutated_ft_100_5_2.txt`
+
+All models are trained with the same hyperparameters (`emb_size=100, window=5, min_count=2, n_epochs=100`) and saved as `KeyedVectors` (see [Gensim Documentation](https://radimrehurek.com/gensim/models/keyedvectors.html)).
+
+### Usage
+
+```python
+from gensim.models import KeyedVectors
+from huggingface_hub import hf_hub_download
+
+model_path = hf_hub_download(repo_id="ancatmara/middle-irish-ft-vectors", filename="middle_irish_cased_ft_100_5_2.txt")
+model = KeyedVectors.load_word2vec_format(model_path, binary=False)
+
+model.similar_by_word('Temra')
+```
+
+Out:
+```python
+>>> [('Temrach', 0.6949042677879333),
+     ('Temraig', 0.6130734086036682),
+     ('Temraich', 0.5354859828948975),
+     ('Mide', 0.49614325165748596),
+     ('Mumam', 0.49278897047042847),
+     ('aenach', 0.4891957640647888),
+     ('Midi', 0.4783679246902466),
+     ('Muman', 0.47727957367897034),
+     ('Lagen', 0.4697839319705963),
+     ('Erenn', 0.4670616388320923)]
+```