README.md

metadata

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 dataset and Happy Transformer framework. 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 final accuracy of 90%

Usage

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(correction.text.find(" .")):
    correction.text=correction.text.replace(" .", ".")

print(correction.text) # Correction: "What is your name?".