Spaces:
Runtime error
Runtime error
Upload 2 files
Browse files- app.py +91 -0
- requirements.txt +82 -0
app.py
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import openai
|
3 |
+
from pytube import YouTube
|
4 |
+
import os
|
5 |
+
from pathlib import Path
|
6 |
+
import shutil
|
7 |
+
import whisper
|
8 |
+
from dotenv import load_dotenv
|
9 |
+
from zipfile import ZipFile
|
10 |
+
|
11 |
+
load_dotenv()
|
12 |
+
|
13 |
+
openai.api_key = os.getenv("OPENAI_API_KEY")
|
14 |
+
|
15 |
+
@st.cache_data
|
16 |
+
def load_model():
|
17 |
+
model = whisper.load_model("base")
|
18 |
+
return model
|
19 |
+
|
20 |
+
def save_audio(url):
|
21 |
+
yt = YouTube(url)
|
22 |
+
video = yt.streams.filter(only_audio=True).first()
|
23 |
+
out_file = video.download()
|
24 |
+
base, ext = os.path.splitext(out_file)
|
25 |
+
file_name = base + '.mp3'
|
26 |
+
try:
|
27 |
+
os.rename(out_file, file_name)
|
28 |
+
except WindowsError:
|
29 |
+
os.remove(file_name)
|
30 |
+
os.rename(out_file, file_name)
|
31 |
+
audio_filename = Path(file_name).stem+'.mp3'
|
32 |
+
print(yt.title + " Has been successfully downloaded")
|
33 |
+
print(file_name)
|
34 |
+
return yt.title, audio_filename
|
35 |
+
|
36 |
+
def audio_to_transcript(audio_file):
|
37 |
+
model = load_model()
|
38 |
+
result = model.transcribe(audio_file)
|
39 |
+
transcript = result["text"]
|
40 |
+
return transcript
|
41 |
+
|
42 |
+
def text_to_news_article(text):
|
43 |
+
response = openai.Completion.create(
|
44 |
+
model="text-davinci-003",
|
45 |
+
prompt="Write a news article in 500 words from the below text:\n"+text,
|
46 |
+
temperature=0.7,
|
47 |
+
max_tokens=600,
|
48 |
+
top_p=1,
|
49 |
+
frequency_penalty=0,
|
50 |
+
presence_penalty=0
|
51 |
+
)
|
52 |
+
return response['choices'][0]['text']
|
53 |
+
|
54 |
+
|
55 |
+
st.markdown('# 📝 **News Article Generator App**')
|
56 |
+
|
57 |
+
st.header('Input the Video URL')
|
58 |
+
|
59 |
+
url_link = st.text_input('Enter URL of YouTube video:')
|
60 |
+
|
61 |
+
if st.checkbox('Start Analysis'):
|
62 |
+
video_title, audio_filename = save_audio(url_link)
|
63 |
+
st.audio(audio_filename)
|
64 |
+
transcript = audio_to_transcript(audio_filename)
|
65 |
+
st.header("Transcript are getting generated...")
|
66 |
+
st.success(transcript)
|
67 |
+
st.header("News Article")
|
68 |
+
result = text_to_news_article(transcript)
|
69 |
+
st.success(result)
|
70 |
+
|
71 |
+
#save the files
|
72 |
+
transcript_txt = open('transcript.txt', 'w')
|
73 |
+
transcript_txt.write(transcript)
|
74 |
+
transcript_txt.close()
|
75 |
+
|
76 |
+
article_txt = open('article.txt', 'w')
|
77 |
+
article_txt.write(result)
|
78 |
+
article_txt.close()
|
79 |
+
|
80 |
+
zip_file = ZipFile('output.zip', 'w')
|
81 |
+
zip_file.write('transcript.txt')
|
82 |
+
zip_file.write('article.txt')
|
83 |
+
zip_file.close()
|
84 |
+
|
85 |
+
with open("output.zip", "rb") as zip_download:
|
86 |
+
btn = st.download_button(
|
87 |
+
label="Download ZIP",
|
88 |
+
data=zip_download,
|
89 |
+
file_name="output.zip",
|
90 |
+
mime="application/zip"
|
91 |
+
)
|
requirements.txt
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
aiohttp==3.8.5
|
2 |
+
aiosignal==1.3.1
|
3 |
+
altair==5.1.2
|
4 |
+
async-timeout==4.0.3
|
5 |
+
attrs==23.1.0
|
6 |
+
blinker==1.6.2
|
7 |
+
cachetools==5.3.1
|
8 |
+
certifi==2023.7.22
|
9 |
+
charset-normalizer==3.3.0
|
10 |
+
click==8.1.7
|
11 |
+
cmake==3.27.6
|
12 |
+
filelock==3.12.4
|
13 |
+
frozenlist==1.4.0
|
14 |
+
gitdb==4.0.10
|
15 |
+
GitPython==3.1.37
|
16 |
+
idna==3.4
|
17 |
+
importlib-metadata==6.8.0
|
18 |
+
Jinja2==3.1.2
|
19 |
+
jsonschema==4.19.1
|
20 |
+
jsonschema-specifications==2023.7.1
|
21 |
+
lit==17.0.2
|
22 |
+
llvmlite==0.41.0
|
23 |
+
markdown-it-py==3.0.0
|
24 |
+
MarkupSafe==2.1.3
|
25 |
+
mdurl==0.1.2
|
26 |
+
more-itertools==10.1.0
|
27 |
+
mpmath==1.3.0
|
28 |
+
multidict==6.0.4
|
29 |
+
networkx==3.1
|
30 |
+
numba==0.58.0
|
31 |
+
numpy==1.25.2
|
32 |
+
nvidia-cublas-cu11==11.10.3.66
|
33 |
+
nvidia-cuda-cupti-cu11==11.7.101
|
34 |
+
nvidia-cuda-nvrtc-cu11==11.7.99
|
35 |
+
nvidia-cuda-runtime-cu11==11.7.99
|
36 |
+
nvidia-cudnn-cu11==8.5.0.96
|
37 |
+
nvidia-cufft-cu11==10.9.0.58
|
38 |
+
nvidia-curand-cu11==10.2.10.91
|
39 |
+
nvidia-cusolver-cu11==11.4.0.1
|
40 |
+
nvidia-cusparse-cu11==11.7.4.91
|
41 |
+
nvidia-nccl-cu11==2.14.3
|
42 |
+
nvidia-nvtx-cu11==11.7.91
|
43 |
+
openai==0.28.1
|
44 |
+
openai-whisper @ git+https://github.com/openai/whisper.git@0a60fcaa9b86748389a656aa013c416030287d47
|
45 |
+
packaging==23.2
|
46 |
+
pandas==2.1.1
|
47 |
+
Pillow==10.0.1
|
48 |
+
protobuf==4.24.4
|
49 |
+
pyarrow==13.0.0
|
50 |
+
pydeck==0.8.1b0
|
51 |
+
pydub==0.25.1
|
52 |
+
Pygments==2.16.1
|
53 |
+
python-dateutil==2.8.2
|
54 |
+
python-dotenv==1.0.0
|
55 |
+
pytube==15.0.0
|
56 |
+
pytz==2023.3.post1
|
57 |
+
referencing==0.30.2
|
58 |
+
regex==2023.10.3
|
59 |
+
requests==2.31.0
|
60 |
+
rich==13.6.0
|
61 |
+
rpds-py==0.10.3
|
62 |
+
six==1.16.0
|
63 |
+
smmap==5.0.1
|
64 |
+
streamlit==1.27.2
|
65 |
+
sympy==1.12
|
66 |
+
tenacity==8.2.3
|
67 |
+
tiktoken==0.3.3
|
68 |
+
toml==0.10.2
|
69 |
+
toolz==0.12.0
|
70 |
+
torch==2.0.1
|
71 |
+
tornado==6.3.3
|
72 |
+
tqdm==4.66.1
|
73 |
+
triton==2.0.0
|
74 |
+
typing_extensions==4.8.0
|
75 |
+
tzdata==2023.3
|
76 |
+
tzlocal==5.1
|
77 |
+
urllib3==2.0.6
|
78 |
+
validators==0.22.0
|
79 |
+
watchdog==3.0.0
|
80 |
+
whisper==1.1.10
|
81 |
+
yarl==1.9.2
|
82 |
+
zipp==3.17.0
|