import torch
import gradio as gr
from PIL import Image
import scipy.io.wavfile as wavfile

# Use a pipeline as a high-level helper
from transformers import pipeline

device = "cuda" if torch.cuda.is_available() else "cpu"
caption_image = pipeline("image-to-text",
                model="Salesforce/blip-image-captioning-large", device=device)
def caption_my_image(pil_image):
    semantics = caption_image(images=pil_image)[0]['generated_text']
    return semantics
demo = gr.Interface(fn=caption_my_image,
                    inputs=[gr.Image(label="Select Image",type="pil")],
                    outputs=[gr.Textbox(label="Image Caption")],
                    title="Image Captioning",
                    description="THIS APPLICATION WILL BE USED TO CAPTION THE IMAGE.")
demo.launch()