py file for Malay headlines writer app

app.py

@@ -0,0 +1,63 @@
+import gradio as gr
+import re
+
+from transformers import (
+    AutoTokenizer,
+    AutoModelForSeq2SeqLM,
+)
+
+def clean_text(text):
+    text = text.encode("ascii", errors="ignore").decode(
+        "ascii"
+    )  # remove non-ascii, Chinese characters
+    text = re.sub(r"http\S+", "", text)
+    text = re.sub(r"\n", " ", text)
+    text = re.sub(r"\n\n", " ", text)
+    text = re.sub(r"\t", " ", text)
+    text = text.strip(" ")
+    text = re.sub(
+        " +", " ", text
+    ).strip()  # get rid of multiple spaces and replace with a single
+    return text
+
+
+model_name = "chinhon/pegasus-newsroom-malay_headlines"
+
+def headline_writer(text):
+    input_text = clean_text(text)
+
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+    model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+    with tokenizer.as_target_tokenizer():
+        batch = tokenizer(
+            input_text,
+            truncation=True,
+            max_length=1024,
+            padding="longest",
+            return_tensors="pt",
+        )
+
+    raw_write = model.generate(**batch)
+
+    headline = tokenizer.batch_decode(
+        raw_write, skip_special_tokens=True, min_length=100, length_penalty=100.1
+    )
+
+    return headline[0]
+
+
+gradio_ui = gr.Interface(
+    fn=headline_writer,
+    title="Malay News Headlines Generator",
+    description="Too busy or tired to write a headline? Try this instead.",
+    inputs=gr.inputs.Textbox(
+        lines=20, label="Paste the first few paras of a Malay language news story here"
+    ),
+    outputs=gr.outputs.Textbox(label="Suggested Headline"),
+    theme="darkdefault"
+)
+
+
+gradio_ui.launch()