Have you ever Imagined what would it be like if we can enter #keywords and #AI converts them to #Sentences?
Presenting #Keytotext!
Keytotext is built using the amazing #T5 model by Google. To simplify the usage I have created a #PyPi Installation:
$ pip install keytotext
I have also created an on-demand Inference API which is built using #FastAPI and Hosted in a Docker, Inc Container. Docker: hub.docker.com/r/gagan30/keyt…
In order to build the Streamlit UI for keytotext, I needed to have a keyword entry method which is why I created streamlit-tags.
UI: share.streamlit.io/gagan3012/keyt…
Streamlit-tags: github.com/gagan3012/stre…
A GPU-enabled #colab notebook has been set up for testing Link in #comments
Colab: colab.research.google.com/github/gagan30…
GitHub: github.com/gagan3012/keyt…
Thanks to @mrm8488 New models have been added to keytotext check out the colab link above!

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Gagan Bhatia

Gagan Bhatia Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!

:(