Upload app.py

app.py

@@ -0,0 +1,64 @@
+import gradio as gr
+import re
+
+from transformers import (
+    BertTokenizer,
+    BartForConditionalGeneration,
+    pipeline
+)
+
+#DEFINE TEXT CLEANING FUNCTION
+def clean_text(text):
+    text = re.sub(r"http\S+", "", text)
+    text = re.sub(r"ADVERTISEMENT", " ", text)
+    text = re.sub(r"ADVERTISING", " ", 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
+
+#Define headlne writer functon
+model_name = "chinhon/bart-large-chinese-cnhdwriter"
+
+tokenizer = BertTokenizer.from_pretrained(model_name, model_max_length=512)
+
+model = BartForConditionalGeneration.from_pretrained(model_name)
+
+text2text_generator = pipeline(
+    "text2text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    truncation=True
+)
+
+def cn_text(text):
+    input_text = clean_text(text)
+
+    prediction = text2text_generator(
+        input_text,
+        max_length=128,
+        length_penalty=50.,
+    )
+
+    pred_text = [x.get("generated_text") for x in prediction]
+
+    return pred_text[0]
+
+
+#3 Define Gradio UI
+gradio_ui = gr.Interface(
+    fn=cn_text,
+    title="Chinese News Headlines Generator",
+    description="Too busy or tired to write a headline for your Chinese news story? Try this instead.",
+    inputs=gr.inputs.Textbox(
+        lines=20, label="Paste Chinese text here"
+    ),
+    outputs=gr.outputs.Textbox(label="Suggested Headline"),
+    theme="huggingface",
+)
+
+gradio_ui.launch(enable_queue=True)