Spaces:
Sleeping
Sleeping
update app file for space for summarisation from russian text
Browse files
app.py
CHANGED
@@ -1,79 +1,26 @@
|
|
1 |
import gradio as gr
|
2 |
-
import
|
3 |
-
import
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
sent_length += len(line.split())
|
27 |
-
data = tmp_data
|
28 |
-
lstm_length = int(sent_length / len(data))
|
29 |
-
|
30 |
-
token = tf.keras.preprocessing.text.Tokenizer()
|
31 |
-
token.fit_on_texts(data)
|
32 |
-
encoded_text = token.texts_to_sequences(data)
|
33 |
-
# Vocabular size
|
34 |
-
vocab_size = len(token.word_counts) + 1
|
35 |
-
|
36 |
-
datalist = []
|
37 |
-
for d in encoded_text:
|
38 |
-
if len(d) > 1:
|
39 |
-
for i in range(2, len(d)):
|
40 |
-
datalist.append(d[:i])
|
41 |
-
|
42 |
-
max_length = 20
|
43 |
-
sequences = tf.keras.preprocessing.sequence.pad_sequences(datalist, maxlen=max_length, padding='pre')
|
44 |
-
|
45 |
-
# X - input data, y - target data
|
46 |
-
X = sequences[:, :-1]
|
47 |
-
y = sequences[:, -1]
|
48 |
-
|
49 |
-
y = tf.keras.utils.to_categorical(y, num_classes=vocab_size)
|
50 |
-
seq_length = X.shape[1]
|
51 |
-
print(f"Sequence length: {seq_length}")
|
52 |
-
|
53 |
-
generated_text = ''
|
54 |
-
number_lines = 3
|
55 |
-
for i in range(number_lines):
|
56 |
-
text_word_list = []
|
57 |
-
for _ in range(lstm_length * 2):
|
58 |
-
encoded = token.texts_to_sequences([seed_text])
|
59 |
-
encoded = tf.keras.preprocessing.sequence.pad_sequences(encoded, maxlen=seq_length, padding='pre')
|
60 |
-
|
61 |
-
y_pred = np.argmax(model.predict(encoded), axis=-1)
|
62 |
-
|
63 |
-
predicted_word = ""
|
64 |
-
for word, index in token.word_index.items():
|
65 |
-
if index == y_pred:
|
66 |
-
predicted_word = word
|
67 |
-
break
|
68 |
-
|
69 |
-
seed_text = seed_text + ' ' + predicted_word
|
70 |
-
text_word_list.append(predicted_word)
|
71 |
-
|
72 |
-
seed_text = text_word_list [-1]
|
73 |
-
generated_text = ' '.join(text_word_list)
|
74 |
-
generated_text += '\n'
|
75 |
-
|
76 |
-
return generated_text
|
77 |
-
|
78 |
-
demo = gr.Interface(fn=generate_from_saved, inputs="text", outputs="text")
|
79 |
demo.launch(share=True)
|
|
|
1 |
import gradio as gr
|
2 |
+
import torch
|
3 |
+
from transformers import GPT2Tokenizer, T5ForConditionalGeneration
|
4 |
+
|
5 |
+
|
6 |
+
tokenizer = GPT2Tokenizer.from_pretrained('RussianNLP/FRED-T5-Summarizer', eos_token='</s>')
|
7 |
+
model = T5ForConditionalGeneration.from_pretrained('RussianNLP/FRED-T5-Summarizer')
|
8 |
+
device = 'cuda'
|
9 |
+
model.to(device)
|
10 |
+
|
11 |
+
input_text = "<LM> Сократи текст.\n "
|
12 |
+
|
13 |
+
def make_summarization(user_text):
|
14 |
+
processing_text = input_text + user_text
|
15 |
+
input_ids = torch.tensor([tokenizer.encode(processing_text)]).to(device)
|
16 |
+
outputs = model.generate(input_ids, eos_token_id=tokenizer.eos_token_id,
|
17 |
+
num_beams=3,
|
18 |
+
min_new_tokens=17,
|
19 |
+
max_new_tokens=200,
|
20 |
+
do_sample=True,
|
21 |
+
no_repeat_ngram_size=4,
|
22 |
+
top_p=0.9)
|
23 |
+
return tokenizer.decode(outputs[0][1:])
|
24 |
+
|
25 |
+
demo = gr.Interface(fn=make_summarization, inputs="text", outputs="text")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
demo.launch(share=True)
|