Create your own writing assistant

:wave: Please read the topic category description to understand what this is all about

Description

Many email and word processing applications can now automatically detect and correct common grammatical errors as you write. For example, the sentence “I am doing fine. How is you?” might be corrected to “I am doing fine. How are you?”. The goal of this project is to fine-tune a Transformer model to be able to automatically provide these corrections, similar to how Grammarly does

Model(s)

This task can be viewed as a sequence-to-sequence task, so models like T5 would be a great starting point

Datasets

Challenges

If you use T5, you’ll need to define a suitable prefix for the text-to-text task. You’ll also need to think about suitable metrics for the evaluation.

Desired project outcomes

  • Create a Streamlit or Gradio app on :hugs: Spaces that can automatically provide suggestions to improve the grammar of some input text. Check out Grammarly for some inspiration on the visualization side.
  • Don’t forget to push all your models and datasets to the Hub so others can build on them!

Additional resources

Discord channel

To chat and organise with other people interested in this project, head over to our Discord and:

  • Follow the instructions on the #join-course channel
  • Join the writing-assistant channel

Just make sure you comment here to indicate that you’ll be contributing to this project :slight_smile:

Team organization on the Hub

To join this team, make sure you join the following organisation on the Hub:

2 Likes

Hi, I am Ashish and I am interested in this project and would like to build it.

3 Likes

Hey @Modfiededition, great to hear that you’re interested in this project! I’ve created a Discord channel (details in the topic description) for you and others join :slight_smile:

Hi, I am not able to find the discord channel for this project.

Hey! I am Satpal and would be contributing to this project.

1 Like

Hey @Modfiededition, did you find the channel in the end? I see there is already someone called Ashish in the channel. If not, you first need to follow the instructions on the #join-course channel, which will then give you access to the project channels :slight_smile:

@lewtun I got the channel. Sorry, for the inconvenience.

1 Like

Hey @Modfiededition and @satpalsr, I’ve created an organisation on the Hub for your team so that you can push your models there and deploy your Streamlit / Gradio application :slight_smile:

See the topic description for the link

1 Like

Hi, I am also interested to this topic. I always wanted to know how grammarly works

1 Like

Hey! @lewtun I would like to build this project individually. So, do I need to push my model to this organisation on the Hub?

Hey @Modfiededition, you’re certainly welcome to build the project by yourself :slight_smile:

In that case, you can push the models and Space to your Hub account - just drop a link here to the Space so we can check it at the end of the event!

hey @lewtun, please check the below screenshot. I don’t understand why I am getting this error on the Hub Inference API.
here is my hub model card link: https://huggingface.co/Modfiededition/t5-base-fine-tuned-jfleg?text=this+is+bads

Hey @Modfiededition it seems that your tokenizer is somehow missing files like tokenizer.json. What happens if you run tokenizer.push_to_hub()?

Hey @lewtun , I have successfully built the Course project: " Create your own writing assistant".

Please find below my hub model card and Space link for this project.

Hub Model Card Link: Modfiededition/t5-base-fine-tuned-on-jfleg · Hugging Face
Space Link: Writing_Assistant - a Hugging Face Space by Modfiededition

Thanks & Regards:

Ashish Goyal
Email id: ashishgy77@gmail.com

1 Like

This is sooo cool @Modfiededition !

It really works nicely :slight_smile:

1 Like

Actually, I am thankful to you @lewtun and all the huggingface team members for creating this wonderful course. I am only able to build this cool project because of the course. The content is also so easy to understand and I just couldn’t stop loading pre-trained models and fine tuning them on different tasks :sweat_smile:

2 Likes

Thank you for the very kind words @Modfiededition :heart: It’s a real pleasure to hear that the course is useful and enabling people like yourself to build these cool applications!

1 Like