Inverse Text Normalization

About The Project

My project is called Inverse Text Normalization. This project is based on Neural Models of Text Normalization for Speech Applications. However, I applied it to the Inverse Text Normalization downstream task. Furthermore, I improved the results by utilizing the Transformer mechanism. Specifically, I used the bert2BERT architecture.

Getting Started

To get started, you should have prior knowledge on Python and Pytorch at first. A few resources to get you started if this is your first Python or Tensorflow project:

• Pytorch Tutorials
• Python for Beginners

Installation and Run

1. Clone the repo

   git clone https://github.com/phkhanhtrinh23/inverse_text_normalization.git

2. Use any code editor to open the folder inverse_text_normalization.

Step-by-step

1. The dataset is: spoken_norm_assignment from a VietAI's course that I studied.

2. Read and run main.py to train the bert2BERT model.

3. Read and run infer.py to predict the results. My checkpoint is saved here.

Results

Contribution

Contributions are what make GitHub such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the project
2. Create your Contribute branch: git checkout -b contribute/Contribute
3. Commit your changes: git commit -m 'add your messages'
4. Push to the branch: git push origin contribute/Contribute
5. Open a pull request

Contact

Email: phkhanhtrinh23@gmail.com