Added logistic regression language classifier model

README.md

@@ -1,40 +1,4 @@
----
-license: mit
-language:
-- ru
-pipeline_tag: text-classification
-tags:
-- tuvan
-- russian
-- binary classifier
----
-# GitHub
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-TuRu - Tuvan/Russian binary classifier model [GitHub](https://github.com/tarbagan/tuvalang/tree/main/turu).
-
-
-## How to use
-
-
-
-```python
-from tensorflow.keras.models import load_model
-
-model = load_model('turu.h5')
-
-text_to_predict = ["""
-Президент ооң бодалы-биле алырга, регионалдыг-даа, муниципалдыг-даа деңнелде деткиир ужурлуг регионнарда спортчу инфраструктура хөгжүлдезиниң айтырыын көрген.
-Ооң келир үеде президент программазының угланыышкыны ол апаарын Владимир Путин чугаалаан.
-"""]
-
-sequences = tokenizer.texts_to_sequences(text_to_predict)
-padded = pad_sequences(sequences, maxlen=10)
-
-prediction = model.predict(padded)
-print(prediction)
-
-```
 
+# Language Classifier
 
+This model is trained to classify text as either Russian or Tuvan language.

config.json

@@ -0,0 +1,6 @@
+
+{
+    "model_type": "logistic_regression",
+    "language": ["russian", "tuvan"],
+    "pipeline_tag": "text-classification"
+}

model/language_classifier.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93552bc0072004f7cceece81b1ffd546743d530c55d00fe1dd7703e5a35b87b6
+size 14610753

model_card.md

@@ -0,0 +1,11 @@
+
+---
+tags:
+- language-classification
+- russian
+- tuvan
+---
+
+# Language Classifier
+
+This model is trained to classify text as either Russian or Tuvan language. It is based on a logistic regression classifier.