added

app.py

@@ -1,22 +1,39 @@
 import gradio as gr
-import torch
-from transformers import BertTokenizerFast, EncoderDecoderModel
+import re
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
-device = 'cuda' if torch.cuda.is_available() else 'cpu'
-ckpt = "csebuetnlp/mT5_multilingual_XLSum"
-tokenizer = BertTokenizerFast.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")
-model = EncoderDecoderModel.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")
+WHITESPACE_HANDLER = lambda k: re.sub('\s+', ' ', re.sub('\n+', ' ', k.strip()))
+
+model_name = "csebuetnlp/mT5_multilingual_XLSum"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
 
 def generate_summary(text):
 
-   inputs = tokenizer([text], padding="max_length", truncation=True, max_length=512, return_tensors="pt")
-   input_ids = inputs.input_ids.to(device)
-   attention_mask = inputs.attention_mask.to(device)
-   output = model.generate(input_ids, attention_mask=attention_mask)
-   return tokenizer.decode(output[0], skip_special_tokens=True)
+   input_ids = tokenizer(
+    [WHITESPACE_HANDLER(text)],
+    return_tensors="pt",
+    padding="max_length",
+    truncation=True,
+    max_length=512)["input_ids"]
+
+   output_ids = model.generate(
+       input_ids=input_ids,
+       max_length=84,
+       no_repeat_ngram_size=2,
+       num_beams=4
+   )[0]
+
+   summary = tokenizer.decode(
+       output_ids,
+       skip_special_tokens=True,
+       clean_up_tokenization_spaces=False
+   )
+
+   return summary
 
 demo = gr.Interface(fn=generate_summary,
-                    inputs=gr.Textbox(lines=10, placeholder="Insert the text here"),
+                    inputs=gr.Textbox(lines=10, placeholder="Matinni kiriting!"),
                     outputs=gr.Textbox(lines=4)
                     )
 

requirements.txt

@@ -1,3 +1,3 @@
 gradio
-torch
+re
 transformers