Delete app.py

app.py

@@ -1,51 +0,0 @@
-import gradio as gr
-from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
-from qwen_vl_utils import process_vision_info
-from PIL import Image
-import torch
-
-# Function to load the model and processor
-@torch.inference_mode()
-def load_model():
-    model_name = "Qwen/Qwen2-VL-2B-Instruct"
-    model = Qwen2VLForConditionalGeneration.from_pretrained(model_name, trust_remote_code=True)
-    processor = AutoProcessor.from_pretrained(model_name)
-    return model, processor
-
-# Load the model and processor
-model, processor = load_model()
-
-# Function to process the image and extract text
-def ocr_from_image(image):
-    image = Image.open(image).convert('RGB')
-
-    # Prepare input for the model
-    messages = [{
-        "role": "user",
-        "content": [
-            {
-                "type": "image",
-                "image": image,
-            },
-            {"type": "text", "text": "Extract the text from the image"},
-        ]
-    }]
-    
-    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-    image_inputs, video_inputs = process_vision_info(messages)
-    inputs = processor(text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt")
-
-    # Generate the output
-    generated_ids = model.generate(**inputs, max_new_tokens=128)
-    generated_ids_trimmed = [out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
-    output_text = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)
-    
-    return output_text[0]
-
-# Define the Gradio interface
-def interface(image):
-    result = ocr_from_image(image)
-    return result
-
-# Gradio app layout
-gr.Interface(fn=interface, inputs="image", outputs="text", title="OCR Web App using Qwen2-VL").launch()