Upload 2 files

app.py

@@ -0,0 +1,41 @@
+import gradio as gr
+
+import torch
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+## Model
+
+access_token = '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'
+tokenizer = AutoTokenizer.from_pretrained("PhongLT/ViLexNorm-bartpho-syllable-base-10e-nopre", token=access_token)
+model = AutoModelForSeq2SeqLM.from_pretrained("PhongLT/ViLexNorm-bartpho-syllable-base-10e-nopre", token=access_token)
+
+
+def normalize(source_text):
+    input_ids = tokenizer(  source_text, 
+                            return_tensors="pt", 
+                            max_length=512, 
+                            padding="max_length", 
+                            truncation= True).input_ids
+
+    output_ids = model.generate(input_ids, 
+                                max_length=512)
+
+    return tokenizer.decode(output_ids[0], 
+                            skip_special_tokens=True, 
+                            max_length=512)
+
+# Create title, description and article strings
+title = "Lexical Normalization Test"
+description = ""
+example_list = ["cl j v tr", "kh hỉu c đg nghĩ j nựa"]
+
+demo = gr.Interface(fn=normalize,
+                    inputs="text", 
+                    outputs="text", 
+                    examples=example_list, 
+                    title=title,
+                    description=description)
+
+# Launch the demo!
+demo.launch(debug=False, # print errors locally?
+            share=True) # generate a publically shareable URL?

requirements.txt

@@ -0,0 +1,3 @@
+torch
+transformers
+sentencepiece