gradio

app.py

@@ -0,0 +1,46 @@
+from html import unescape
+from unicodedata import normalize
+import gradio as gr
+from transformers import pipeline
+import re
+
+re_multispace = re.compile(r"\s+")
+
+def normalize_text(text):
+    if text == None:
+        return None
+
+    text = text.strip()
+    text = text.replace("\n", " ")
+    text = text.replace("\t", " ")
+    text = text.replace("\r", " ")
+    text = re_multispace.sub(" ", text)
+    text = unescape(text)
+    text = normalize("NFKC", text)
+    return text
+
+
+models = [
+    "Server", "Category", "Gender", "Day Of Week"
+]
+
+pipelines = {model: pipeline(task="text-classification",
+ model=f"hynky/{model.replace(' ', '_')}", tokenizer="ufal/robeczech-base",
+ return_all_scores=True
+) for model in models}
+
+    
+def predict(article):
+    article = normalize_text(article)
+    predictions = {model: pipelines[model](article) for model in models}
+    return predictions
+
+gr.Interface(
+    predict,
+    inputs=gr.inputs.Textbox(lines=2, placeholder="Paste a news article here..."),
+    # multioutput of gradio text
+    outputs=[gr.outputs.Label(num_top_classses=5)
+    
+    for model in models],
+    title="News Article Classifier",
+).launch()