Update: update fasttext model

.gitignore

@@ -0,0 +1 @@
+fasttext/models

fasttext/model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ded5749a2ad79ae9ab7c9190c7c8b97ff20d54ad8b9527ffa50107238fc7f6a
-size 1176355829

lid.py

@@ -1,16 +1,23 @@
+import os
 import fasttext
 from huggingface_hub import hf_hub_download
 import matplotlib.pyplot as plt
 import seaborn as sns
 
-# Download the model from Hugging Face Hub
-# model_path = hf_hub_download(
-#     # repo_id="cis-lmu/glotlid", filename="model.bin", cache_dir="./glotlid"
-#     repo_id="facebook/fasttext-language-identification",
-#     filename="model.bin",
-#     cache_dir="fasttext",
-# )
-model = fasttext.load_model("fasttext/model.bin")
+
+def load_model(repo_id: str) -> fasttext.FastText._FastText:
+    model_path = hf_hub_download(
+        repo_id,
+        filename="model.bin",
+        cache_dir="fasttext/models",
+    )
+
+    return fasttext.load_model(model_path)
+
+
+# repo_id="cis-lmu/glotlid"
+repo_id = "facebook/fasttext-language-identification"
+model = load_model(repo_id)
 
 
 def identify_languages(title):