Showcase Your Projects in Spaces using Gradio

Summary

Demonstrating machine learning projects to the community requires accessible hosting and minimal interface boilerplate. Gradio integrates directly with the Hugging Face Hub and its underlying Inference API, enabling developers to load models using repository identifiers and launch interactive interfaces with a few lines of code. Hugging Face Spaces provides a free hosting environment where users select Gradio as the SDK, commit an app.py script, and deploy live web demonstrations for frameworks like Transformers, spaCy, SpeechBrain, and Asteroid. For complex workflows, developers can chain multiple models sequentially via Gradio Series or host custom checkpoints directly when models lack native Inference API support.

Context

Sharing and demonstrating machine learning models publicly requires hosting solutions and functional user interfaces without introducing significant development overhead.

Approach / What changed

Developers define a Gradio Interface via gr.Interface.load using Hugging Face Hub model IDs, configure metadata and examples, and deploy the application to Hugging Face Spaces using the Gradio SDK. Workflows can also combine multiple models sequentially using Gradio Series or wrap custom inference checkpoints directly.

Takeaways

• Gradio connects with the Hugging Face Inference API via gr.Interface.load, supporting tasks across frameworks including Transformers, spaCy, SpeechBrain, and Asteroid.
• Hugging Face Spaces provides free hosting for Python ML demo applications using Git or drag-and-drop file uploads containing an app.py script configured with the Gradio SDK.
• Gradio Series enables chaining multiple distinct models together, such as linking translation models before and after a story generator.

Related reading

• huggingface.co · May 17, 2022

  Announcing the Hugging Face Fellowship Program

  Hugging Face announced the launch of the Hugging Face Fellowship Program to support and empower prominent contributors across the open-source machine learning ecosystem. The initiative provides selected fellows with personalized resources according to their project goals, including computing power, merchandise, and official recognition from Hugging Face. Candidate selection operates on an ongoing basis through nominations made by Hugging Face team members or existing fellows, evaluated primarily on past contributions toward democratizing machine learning. Eligible open-source activities span model releases on the Hub, documentation translations, library tooling improvements for frameworks like TensorFlow and Keras, and community hackathons. Participation does not constitute employment with Hugging Face, though the program serves as a platform to scale grassroots community impact across diverse machine learning domains.

  merve, Omar Espejel

• huggingface.co · May 25, 2021

  Using & Mixing Hugging Face Models with Gradio 2.0

  The Hugging Face Model Hub hosts more than 10,000 user-submitted machine learning models spanning natural language processing, image classification, and audio processing. Machine learning developers increasingly need to demo models to interdisciplinary collaborators or non-programmers to uncover biases and failure points. The Gradio 2.0 library enables users to create graphical user interfaces and load almost any Hugging Face model using a single line of code. By default, these interfaces query Hugging Face's hosted Inference API without requiring an API key, though users can also run computations locally via the transformers library. Gradio interfaces can be customized through the Interface class and composed to load multiple models in parallel or chain them in series.