Upload 2 files

app.py

@@ -0,0 +1,40 @@
+import gradio as gr
+from transformers import LayoutLMv3Processor, LayoutLMv3ForTokenClassification
+from PIL import Image
+import pytesseract
+
+# Load model and processor
+model = LayoutLMv3ForTokenClassification.from_pretrained("./model")
+processor = LayoutLMv3Processor.from_pretrained("./model")
+
+# Define label mapping
+id2label = {0: "company", 1: "date", 2: "address", 3: "total", 4: "other"}
+
+def predict_receipt(image):
+    ocr_data = pytesseract.image_to_data(image, output_type=pytesseract.Output.DICT)
+    texts = ocr_data["text"]
+    boxes = [
+        [
+            ocr_data["left"][i],
+            ocr_data["top"][i],
+            ocr_data["left"][i] + ocr_data["width"][i],
+            ocr_data["top"][i] + ocr_data["height"][i],
+        ]
+        for i in range(len(ocr_data["text"]))
+    ]
+    encoding = processor(image, text=texts, boxes=boxes, return_tensors="pt", truncation=True, padding="max_length")
+    outputs = model(**{k: v for k, v in encoding.items()})
+    predictions = outputs.logits.argmax(-1).squeeze().tolist()
+    labeled_output = {id2label[pred]: texts[i] for i, pred in enumerate(predictions) if pred != 4}
+    return labeled_output
+
+interface = gr.Interface(
+    fn=predict_receipt,
+    inputs=gr.Image(type="pil"),
+    outputs="json",
+    title="Receipt Analyzer",
+    description="Upload a receipt image to extract key information."
+)
+
+if __name__ == "__main__":
+    interface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio==3.36
+torch>=1.10.0
+transformers
+pytesseract
+Pillow