import torch from transformers import pipeline from datasets import load_dataset device = "cuda:0" if torch.cuda.is_available() else "cpu" pipe = pipeline( "automatic-speech-recognition", model="openai/whisper-small", chunk_length_s=30, device=device, ) gradio_app = gr.Interface( predict, inputs=gr.Audio(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"), outputs=[gr. Audio(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)], title="Hot Dog? Or Not?", ) if __name__ == "__main__": gradio_app.launch()