Metadata-Version: 2.1
Name: keytotext
Version: 0.1.2
Summary: Text Generation Using Keywords
Home-page: https://github.com/gagan3012/keytotext
Author: Gagan Bhatia
Author-email: gbhatia880@gmail.com
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Requires-Dist: torch
Requires-Dist: transformers


# keytotext

![keytotext](https://socialify.git.ci/gagan3012/keytotext/image?description=1&language=1&owner=1&stargazers=1&theme=Light)

Idea is to build a model which will take keywords as inputs and generate sentences as outputs. 

### Model:

Two Models have been built: 

- Using T5-base size = 850 MB can be found here: https://huggingface.co/gagan3012/keytotext
- Using T5-small size = 230 MB can be found here: https://huggingface.co/gagan3012/keytotext-small
- Updated model: https://huggingface.co/gagan3012/k2t

Models trained as in notebooks

### Usage:

```
pip install keytotext
```

![carbon](https://user-images.githubusercontent.com/49101362/116014804-bd0f9e80-a63f-11eb-9b71-2ff574018dc7.png)


### UI:

This uses a custom streamlit component built by me: [GitHub](https://github.com/gagan3012/streamlit-tags)

```
pip install streamlit-tags
```

![image](https://user-images.githubusercontent.com/49101362/116162205-fc042980-a6fd-11eb-892e-8f6902f193f4.png)


