init project

app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
+import torch
+
+MODEL_ID = "GusRot/blip-flickr8k-finetuned"
+
+processor = BlipProcessor.from_pretrained(MODEL_ID)
+model = BlipForConditionalGeneration.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def generate_alt_text(image: Image.Image):
+    inputs = processor(images=image, return_tensors="pt").to(model.device)
+    
+    output_ids = model.generate(
+        **inputs,
+        max_new_tokens=40
+    )
+    
+    caption = processor.decode(output_ids[0], skip_special_tokens=True)
+    return caption
+
+demo = gr.Interface(
+    fn=generate_alt_text,
+    inputs=gr.Image(type="pil", label="Upload an image"),
+    outputs=gr.Textbox(label="Generated ALT text"),
+    title="ALT Text Generator",
+    description="Generates accessible image descriptions using a fine-tuned BLIP model."
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+transformers
+torch
+accelerate
+pillow
+gradio
+sentencepiece