Interspeech2022

non-profit

AI & ML interests

None defined yet.

Join organization by clicking here

This organization invites participants to showoff conference papers on Hugging Face as a Gradio Web Demo (Note: This is not a official INTERSPEECH sponsored event)

Hugging Face Gradio INTERSPEECH 2022 event

INTERSPEECH organization is accepting Gradio demo submissions for INTERSPEECH 2022 papers from anyone for a chance to win prizes from Hugging Face, see prizes section and the leaderboard below. The deadline to submit demos is September 30th, 2022 (AOE Time Zone). For all participants, feel free to submit Gradio demos for any INTERSPEECH paper for a chance to win prizes, you can submit demos for multiple papers. Find tutorial on getting started with Gradio on Hugging Face here and to get started with the new Gradio Blocks API here

Hugging Face Prizes

LeaderBoard for Most Popular INTERSPEECH Spaces

See the INTERSPEECH Leaderboard

Hugging Face Spaces & Gradio for Showcasing your INTERSPEECH ‘22 Demo

In this tutorial, we will demonstrate how to showcase your demo with an easy to use web interface using the Gradio Python library and host it on Hugging Face Spaces so that conference attendees can easily find and try out your demos. Also, see https://gradio.app/introduction_to_blocks/, for a more flexible way to build Gradio Demos

🚀 Create a Gradio Demo from your Model

The first step is to create a web demo from your model. As an example, we will be creating a demo from an image classification model (called model) which we will be uploading to Spaces. The full code for steps 1-4 can be found in this colab notebook.


1. Install the gradio library

All you need to do is to run this in the terminal: pip install gradio


2. Define a function in your Python code that performs inference with your model on a data point and returns the prediction

Here’s we define our image classification model prediction function in PyTorch (any framework, like TensorFlow, scikit-learn, JAX, or a plain Python will work as well):


def predict(inp):
  inp = Image.fromarray(inp.astype('uint8'), 'RGB')
  

inp = transforms.ToTensor()(inp).unsqueeze(0)

with torch.no_grad():

prediction = torch.nn.functional.softmax(model(inp)[0], dim=0)

return {labels[i]: float(prediction[i]) for i in range(1000)}

3. Then create a Gradio Interface using the function and the appropriate input and output types

For the image classification model from Step 2, it would like like this:


inputs = gr.inputs.Image()

outputs = gr.outputs.Label(num_top_classes=3)

io = gr.Interface(fn=predict, inputs=inputs, outputs=outputs)

If you need help creating a Gradio Interface for your model, check out the Gradio Getting Started guide.

4. Then launch() you Interface to confirm that it runs correctly locally (or wherever you are running Python)


io.launch() 

You should see a web interface like the following where you can drag and drop your data points and see the predictions:

Gradio Interface

models

None public yet

datasets

None public yet