Upload README.md

README.md

@@ -0,0 +1,50 @@
+---
+
+language: en
+
+tags:
+
+- sentence correction
+
+- text-generation
+
+license: cc-by-nc-sa-4.0
+
+datasets:
+
+- jfleg
+
+---
+
+# Model
+This model utilises T5-base sentence correction pre-trained model. It was fine tuned using [JFLEG](https://arxiv.org/abs/1702.04066) dataset and [Happy Transformer framework](https://github.com/EricFillion/happy-transformer). This model was pre-trained for educational purposes only for correction on local caribbean dialect.
+.
+___
+
+
+# Re-training/Fine Tuning
+
+The results of fine-tuning resulted in a finally accuracy of 90%
+
+
+# Usage 
+
+
+
+```python
+
+from happytransformer import HappyTextToText, TTSettings
+
+pre_trained_model="T5"
+model = HappyTextToText(pre_trained_model, "KES/T5-KES")
+
+arguments = TTSettings(num_beams=4, min_length=1)
+sentence = "Wat iz your nam"
+
+correction = model.generate_text("grammar: "+sentence, args=arguments)
+if(result.text.find(" .")):
+    result.text=result.text.replace(" .", ".")
+
+print(result.text) # Correction: "What is your name?".
+
+```