app.py

import gradio as gr
title = "SEW-D-base+"
description = "Gradio demo for SEW-D-base+ for ASR. The base model pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. Note that this model should be fine-tuned on a downstream task, like Automatic Speech Recognition, Speaker Identification, Intent Classification, Emotion Recognition, etc... To use it add your audio or click one of the examples below to load them. Read more at the links below"
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2109.06870' target='_blank'> Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition</a></p>"

gr.Interface.load("huggingface/asapp/sew-d-base-plus-400k-ft-ls100h",
    title=title,
    description=description,
    article=article
).launch()