Spaces:
Runtime error
Runtime error
File size: 3,282 Bytes
b020e81 0fd3cfb 4b9ceb2 0fd3cfb 3995371 1abf4af 3995371 b020e81 0fd3cfb d8843f7 3995371 b020e81 84b29d0 b020e81 3995371 b020e81 d8843f7 b309611 0fd3cfb 1b9db30 b309611 4e2a680 b309611 1b9db30 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 |
from transformers import T5Tokenizer, T5Model, T5ForConditionalGeneration, BertTokenizer, EncoderDecoderModel, AutoTokenizer, AutoModelForSeq2SeqLM
import gradio as gr
from gradio.mix import Parallel
tokenizer_t5 = T5Tokenizer.from_pretrained("panggi/t5-base-indonesian-summarization-cased")
model_t5 = T5ForConditionalGeneration.from_pretrained("panggi/t5-base-indonesian-summarization-cased")
tokenizer_bert = BertTokenizer.from_pretrained("cahya/bert2bert-indonesian-summarization")
tokenizer_bert.bos_token = tokenizer_bert.cls_token
tokenizer_bert.eos_token = tokenizer_bert.sep_token
model_bert = EncoderDecoderModel.from_pretrained("cahya/bert2bert-indonesian-summarization")
t5_para_tokenizer = AutoTokenizer.from_pretrained("Wikidepia/IndoT5-base-paraphrase")
t5_para_model = AutoModelForSeq2SeqLM.from_pretrained("Wikidepia/IndoT5-base-paraphrase")
def summ_t5(text):
input_ids = tokenizer_t5.encode(text, return_tensors='pt')
summary_ids = model_t5.generate(input_ids,
max_length=100,
num_beams=2,
repetition_penalty=2.5,
length_penalty=1.0,
early_stopping=True,
no_repeat_ngram_size=2,
use_cache=True)
summary_text = tokenizer_t5.decode(summary_ids[0], skip_special_tokens=True)
return summary_text
def summ_bert(text):
encoding = tokenizer(text, padding='longest', return_tensors="pt")
outputs = model.generate(
input_ids=encoding["input_ids"], attention_mask=encoding["attention_mask"],
max_length=512,
do_sample=True,
top_k=200,
top_p=0.95,
early_stopping=True,
num_return_sequences=5)
summary_text = tokenizer_bert.decode(summary_ids[0], skip_special_tokens=True)
return summary_text
def para_t5(text):
input_ids = t5_para_tokenizer.encode(text, return_tensors='pt')
outputs = t5_para_model .generate(input_ids,
min_length=20,
max_length=100,
num_beams=10,
repetition_penalty=2.5,
length_penalty=1.0,
early_stopping=True,
no_repeat_ngram_size=2,
use_cache=True,
do_sample = True,
temperature = 0.8,
top_k = 50,
top_p = 0.95)
return [
t5_para_tokenizer.decode(
output, skip_special_tokens=True, clean_up_tokenization_spaces=True
)
for output in outputs
]
def summarize(text):
t5_ = summ_t5(text)
bert_ = summ_bert(text)
para_ = para_t5(t5_)
return t5_, bert_, para_
if __name__ == "__main__":
with gr.Blocks() as demo:
with gr.Row():
with gr.Column():
input_text = gr.Textbox(label="Input Text")
analyze_button = gr.Button(label="Analyze")
with gr.Column():
t5_output = gr.Textbox(label="T5 Base Output")
bert_output = gr.Textbox(label="Bert Base Output")
para_output = gr.Textbox(label="T5 Paraphrase Output")
analyze_button.click(summarize, input_text, [t5_output, bert_output, para_output])
demo.launch() |