Showcase Your Projects in Spaces using Gradio

It's so easy to demonstrate a Machine Learning project thanks to Gradio.

In this blog post, we'll walk you through:

• the recent Gradio integration that helps you demo models from the Hub seamlessly with few lines of code leveraging the Inference API.
• how to use Hugging Face Spaces to host demos of your own models.

Hugging Face Hub Integration in Gradio

You can demonstrate your models in the Hub easily. You only need to define the Interface that includes:

• The repository ID of the model you want to infer with
• A description and title
• Example inputs to guide your audience

After defining your Interface, just call .launch() and your demo will start running. You can do this in Colab, but if you want to share it with the community a great option is to use Spaces!

Spaces are a simple, free way to host your ML demo apps in Python. To do so, you can create a repository at https://huggingface.co/new-space and select Gradio as the SDK. Once done, you can create a file called app.py, copy the code below, and your app will be up and running in a few seconds!

import gradio as gr

description = "Story generation with GPT-2"
title = "Generate your own story"
examples = [["Adventurer is approached by a mysterious stranger in the tavern for a new quest."]]

interface = gr.Interface.load("huggingface/pranavpsv/gpt2-genre-story-generator",
            description=description,
            examples=examples
)

interface.launch()

You can play with the Story Generation model here

Under the hood, Gradio calls the Inference API which supports Transformers as well as other popular ML frameworks such as spaCy, SpeechBrain and Asteroid. This integration supports different types of models, image-to-text, speech-to-text, text-to-speech and more. You can check out this example BigGAN ImageNet text-to-image model here. Implementation is below.

Serving Custom Model Checkpoints with Gradio in Hugging Face Spaces

Mix and Match Models!

You can check out the French Story Generator here