Fix app.py

app.py

@@ -7,74 +7,61 @@ from tokenizer_base import Tokenizer
 import pathlib
 import os
 import gradio as gr
-from huggingface_hub import Repository
-
-# repo = Repository(
-#     local_dir="secret_models",
-#     repo_type="model",
-#     clone_from="docparser/captcha",
-#     token=True
-# )
-# repo.git_pull()
 
 cwd = pathlib.Path(__file__).parent.resolve()
-model_file = os.path.join(cwd,"secret_models","captcha.onnx")
-img_size = (32,128)
+model_file = os.path.join(cwd, "secret_models", "captcha.onnx")
+img_size = (32, 128)
 charset = r"0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"
 tokenizer_base = Tokenizer(charset)
 
 def get_transform(img_size):
-        transforms = []
-        transforms.extend([
-            T.Resize(img_size, T.InterpolationMode.BICUBIC),
-            T.ToTensor(),
-            T.Normalize(0.5, 0.5)
-        ])
-        return T.Compose(transforms)
+    transforms = []
+    transforms.extend([
+        T.Resize(img_size, T.InterpolationMode.BICUBIC),
+        T.ToTensor(),
+        T.Normalize(0.5, 0.5)
+    ])
+    return T.Compose(transforms)
 
 def to_numpy(tensor):
     return tensor.detach().cpu().numpy() if tensor.requires_grad else tensor.cpu().numpy()
 
 def initialize_model(model_file):
     transform = get_transform(img_size)
-    # Onnx model loading
-    onnx_model = onnx.load(model_file)
-    onnx.checker.check_model(onnx_model)
     ort_session = rt.InferenceSession(model_file)
-    return transform,ort_session 
+    return transform, ort_session 
 
 def get_text(img_org):
     try:
-        # img_org = Image.open(image_path)
-        # Preprocess. Model expects a batch of images with shape: (B, C, H, W)
+        if img_org is None:
+            return ""
         x = transform(img_org.convert('RGB')).unsqueeze(0)
-    
-        # compute ONNX Runtime output prediction
         ort_inputs = {ort_session.get_inputs()[0].name: to_numpy(x)}
         logits = ort_session.run(None, ort_inputs)[0]
         probs = torch.tensor(logits).softmax(-1)
         preds, probs = tokenizer_base.decode(probs)
-        preds = preds[0]
-        print(preds)
-        return preds
+        return preds[0]
     except Exception as e:
-        print(str(e))
+        return str(e)
 
-transform,ort_session = initialize_model(model_file=model_file)
+# Inicializamos el modelo una sola vez
+transform, ort_session = initialize_model(model_file=model_file)
 
-gr.Interface(
-    get_text,
+# Creamos la interfaz
+demo = gr.Interface(
+    fn=get_text,
     inputs=gr.Image(type="pil"),
     outputs=gr.Textbox(),
     title="Text Captcha Reader",
     examples=["8000.png","11JW29.png","2a8486.jpg","2nbcx.png",
-             "000679.png","000HU.png","00Uga.png.jpg","00bAQwhAZU.jpg",
-             "00h57kYf.jpg","0EoHdtVb.png","0JS21.png","0p98z.png","10010.png"]
-).launch(server_name="0.0.0.0", server_port=7860)
-
-# if __name__ == "__main__":
-#     image_path = "8000.png"
-#     preds,probs = get_text(image_path)
-#     print(preds[0])
-     
+              "000679.png","000HU.png","00Uga.png.jpg","00bAQwhAZU.jpg",
+              "00h57kYf.jpg","0EoHdtVb.png","0JS21.png","0p98z.png","10010.png"]
+)
 
+# Lanzamiento optimizado para Hugging Face Spaces
+if __name__ == "__main__":
+    demo.launch(
+        server_name="0.0.0.0", 
+        server_port=7860, 
+        show_api=False
+    )