Update app.py

app.py

@@ -1,42 +1,13 @@
-import os
-import torch
-import gradio as gr
 from PIL import Image
-from transformers import AutoProcessor, AutoModelForVision2Seq
-
-hf_token = os.getenv("HUGGINGFACE_TOKEN")
-
-token_args = {}
-if hf_token:
-    token_args = {"use_auth_token": hf_token}
-
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-processor = AutoProcessor.from_pretrained("scb10x/typhoon-ocr-3b", **token_args)
-model = AutoModelForVision2Seq.from_pretrained(
-    "scb10x/typhoon-ocr-3b",
-    torch_dtype=torch.float16,
-    device_map="auto",
-    **token_args
-)
-
-def ocr_infer(image):
-    if image is None:
-        return "❌ Error: No image provided"
-    try:
-        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(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 during inference: {e}"
-
-iface = gr.Interface(fn=ocr_infer, inputs=gr.Image(type="pil"), outputs="text", title="Typhoon OCR 3B")
-iface.launch()
+import requests
+from io import BytesIO
+
+image_url = "https://raw.githubusercontent.com/scb10x/typhoon-ocr/main/assets/test-image.png"
+response = requests.get(image_url)
+image = Image.open(BytesIO(response.content)).convert("RGB")
+
+inputs = processor(images=image, return_tensors="pt")
+inputs = {k: v.to(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]
+print(result)