Switch to Gradio sdk

README.md

@@ -3,7 +3,7 @@ title: Annif - Text Classification and Subject Indexing
 emoji: 📕
 colorFrom: purple
 colorTo: purple
-sdk: docker
+sdk: gradio
 pinned: false
 tags:
 - glam

app.py

@@ -0,0 +1,31 @@
+import gradio as gr, pytesseract, cv2, os
+
+
+def process(image: str, lang: str = "eng") -> str:
+    try:
+        img = cv2.imread(image)
+        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+        threshold_img = cv2.threshold(
+            gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU
+        )[1]
+        result = pytesseract.image_to_string(threshold_img, lang=lang)
+        os.remove(image)
+        return result
+    except Exception as e:
+        return str(e)
+
+
+langs = pytesseract.get_languages()
+
+interface = gr.Interface(
+    process,
+    [
+        gr.Image(type="filepath"),
+        gr.Dropdown(label="Select Language", choices=langs, type="value"),
+    ],
+    outputs="text",
+    css="footer {visibility: hidden}",
+    title="Optical Character Recognition | Image To Text",
+    article="""<p style='text-align: center;'>Hello, thanks for coming, visit our tools: <a href="https://www.genelify.com" target="_blank">Genelify</a></p>""",
+)
+interface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+pytesseract
+gradio
+opencv-python