app.py

import gradio as gr
import os

os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
os.environ["USER"] = "imagecraft"


import gradio as gr
from src.model.modules.imagecraft import ImageCraft

model = ImageCraft.from_pretrained("nsandiman/imagecraft-ft-co-224")


def imagecraft_interface(image_path):
    """Process image inputs and generate audio response."""
    transcript, audio_buffer = model.generate(image_path, output_type="buffer")

    return audio_buffer, transcript


# Define Gradio interface
gradio_interface = gr.Interface(
    fn=imagecraft_interface,
    inputs=[
        gr.Image(type="filepath", label="Upload an image"),
    ],
    outputs=[gr.Audio(label="Speech"), gr.Textbox(label="Transcript")],
    title="ImageCraft",
    description="Upload an image and get the speech responses.",
    flagging_mode="never",
)

if __name__ == "__main__":
    # Launch the Gradio app
    gradio_interface.launch()