Spaces:
Build error
Build error
Commit
•
a4400c8
0
Parent(s):
Duplicate from benthecoder/news-summarizer
Browse filesCo-authored-by: Benedict Neo Yao En <benthecoder@users.noreply.huggingface.co>
- .gitattributes +27 -0
- README.md +38 -0
- app.py +47 -0
- requirements.txt +4 -0
.gitattributes
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
20 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Article Summarizer
|
3 |
+
emoji: 🏃
|
4 |
+
colorFrom: purple
|
5 |
+
colorTo: pink
|
6 |
+
sdk: gradio
|
7 |
+
app_file: app.py
|
8 |
+
pinned: false
|
9 |
+
duplicated_from: benthecoder/news-summarizer
|
10 |
+
---
|
11 |
+
|
12 |
+
# Configuration
|
13 |
+
|
14 |
+
`title`: _string_
|
15 |
+
Display title for the Space
|
16 |
+
|
17 |
+
`emoji`: _string_
|
18 |
+
Space emoji (emoji-only character allowed)
|
19 |
+
|
20 |
+
`colorFrom`: _string_
|
21 |
+
Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
|
22 |
+
|
23 |
+
`colorTo`: _string_
|
24 |
+
Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
|
25 |
+
|
26 |
+
`sdk`: _string_
|
27 |
+
Can be either `gradio` or `streamlit`
|
28 |
+
|
29 |
+
`sdk_version` : _string_
|
30 |
+
Only applicable for `streamlit` SDK.
|
31 |
+
See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
|
32 |
+
|
33 |
+
`app_file`: _string_
|
34 |
+
Path to your main application file (which contains either `gradio` or `streamlit` Python code).
|
35 |
+
Path is relative to the root of the repository.
|
36 |
+
|
37 |
+
`pinned`: _boolean_
|
38 |
+
Whether the Space stays on top of your list.
|
app.py
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from newspaper import Article
|
2 |
+
from newspaper import Config
|
3 |
+
import nltk
|
4 |
+
nltk.download('punkt')
|
5 |
+
|
6 |
+
from transformers import pipeline
|
7 |
+
import gradio as gr
|
8 |
+
from gradio.mix import Parallel, Series
|
9 |
+
|
10 |
+
|
11 |
+
def extract_article_text(url):
|
12 |
+
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:78.0) Gecko/20100101 Firefox/78.0'
|
13 |
+
config = Config()
|
14 |
+
config.browser_user_agent = USER_AGENT
|
15 |
+
config.request_timeout = 10
|
16 |
+
|
17 |
+
article = Article(url, config=config)
|
18 |
+
article.download()
|
19 |
+
article.parse()
|
20 |
+
text = article.text
|
21 |
+
return text
|
22 |
+
|
23 |
+
extractor = gr.Interface(extract_article_text, 'text', 'text')
|
24 |
+
summarizer = gr.Interface.load("huggingface/facebook/bart-large-cnn")
|
25 |
+
|
26 |
+
sample_url = [['https://www.technologyreview.com/2021/07/22/1029973/deepmind-alphafold-protein-folding-biology-disease-drugs-proteome/'],
|
27 |
+
['https://www.technologyreview.com/2021/07/21/1029860/disability-rights-employment-discrimination-ai-hiring/'],
|
28 |
+
['https://www.technologyreview.com/2021/07/09/1028140/ai-voice-actors-sound-human/']]
|
29 |
+
|
30 |
+
desc = '''
|
31 |
+
Let Hugging Face models summarize articles for you.
|
32 |
+
Note: Shorter articles generate faster summaries.
|
33 |
+
This summarizer uses bart-large-cnn model by Facebook
|
34 |
+
'''
|
35 |
+
|
36 |
+
iface = Series(extractor, summarizer,
|
37 |
+
inputs = gr.inputs.Textbox(
|
38 |
+
lines = 2,
|
39 |
+
label = 'URL'
|
40 |
+
),
|
41 |
+
outputs = 'text',
|
42 |
+
title = 'News Summarizer',
|
43 |
+
theme = 'huggingface',
|
44 |
+
description = desc,
|
45 |
+
examples=sample_url)
|
46 |
+
|
47 |
+
iface.launch()
|
requirements.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
gradio==2.4.2
|
2 |
+
newspaper3k==0.2.8
|
3 |
+
nltk==3.6.5
|
4 |
+
transformers==4.12.3
|