Update app.py

app.py

@@ -1,26 +1,40 @@
-from transformers import AutoProcessor, AutoModelForVision2Seq
 import torch
 from PIL import Image
 import gradio as gr
+from transformers import AutoProcessor, AutoModelForVision2Seq
 
-processor = AutoProcessor.from_pretrained("scb10x/typhoon-ocr-1b")
+processor = AutoProcessor.from_pretrained("scb10x/typhoon-ocr-3b", use_auth_token=False)
 model = AutoModelForVision2Seq.from_pretrained(
-    "scb10x/typhoon-ocr-1b",
+    "scb10x/typhoon-ocr-3b",
     torch_dtype=torch.float16,
-    device_map="auto"
+    device_map="auto",
+    use_auth_token=False
 )
 
 def ocr_infer(image):
     try:
+        if image is None:
+            return "❌ Error: No image provided"
+        
         image = image.convert("RGB")
         inputs = processor(images=image, return_tensors="pt")
+        
+        if inputs is None or "pixel_values" not in inputs:
+            return "❌ Error: Invalid processor output"
+        
         inputs = {k: v.to(model.device) for k, v in inputs.items()}
-
         generated_ids = model.generate(**inputs, max_new_tokens=256)
         result = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
         return result
+
     except Exception as e:
-        return f"❌ Error: {e}"
+        return f"❌ Error during inference: {e}"
+
+iface = gr.Interface(
+    fn=ocr_infer,
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    title="Typhoon OCR 3B"
+)
 
-iface = gr.Interface(fn=ocr_infer, inputs=gr.Image(type="pil"), outputs="text", title="Typhoon OCR 1B")
 iface.launch()