Spaces:
Runtime error
Runtime error
import streamlit as st | |
from urllib.parse import urlparse, parse_qs | |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline | |
# https://pypi.org/project/youtube-transcript-api/ | |
from youtube_transcript_api import YouTubeTranscriptApi | |
def get_video_id(url: str) -> str: | |
""" | |
Examples: | |
- http://youtu.be/SA2iWivDJiE | |
- http://www.youtube.com/watch?v=_oPAwA_Udwc&feature=feedu | |
- http://www.youtube.com/embed/SA2iWivDJiE | |
- http://www.youtube.com/v/SA2iWivDJiE?version=3&hl=en_US | |
""" | |
query = urlparse(url) | |
if query.hostname == 'youtu.be': | |
return query.path[1:] | |
if query.hostname in ('www.youtube.com', 'youtube.com'): | |
if query.path == '/watch': | |
p = parse_qs(query.query) | |
return p['v'][0] | |
if query.path[:7] == '/embed/': | |
return query.path.split('/')[2] | |
if query.path[:3] == '/v/': | |
return query.path.split('/')[2] | |
return None | |
def get_youtube_subtitle(video_id: str) -> str: | |
try: | |
parse = YouTubeTranscriptApi.get_transcript(video_id, languages=['ru']) | |
result = '' | |
for i in parse: | |
if (i['text'][0] =='[') & (i['text'][-1] ==']'): continue | |
result += ' ' + i['text'] | |
result = result.strip()[0].upper() + result.strip()[1:] | |
return result.strip() | |
except: | |
return None | |
if __name__ == "__main__": | |
st.header("Annotation of subtitles from YouTube") | |
# st.text('Load model...') | |
# m_name = '/content/drive/MyDrive/Colab Notebooks/Netology/diplom_neto/summarize1' | |
m_name = "csebuetnlp/mT5_multilingual_XLSum" | |
# tokenizer = AutoTokenizer.from_pretrained(m_name) | |
# model = AutoModelForSeq2SeqLM.from_pretrained(m_name) | |
# st.text('Model is loaded') | |
url = st.text_input('Enter the URL of the Youtube video', 'https://www.youtube.com/watch?v=HGSVsK32rKA') | |
video_id = get_video_id(url) | |
if video_id is not None: | |
subtitle = get_youtube_subtitle(video_id) | |
if subtitle is not None: | |
st.subheader('Subtitles') | |
st.text(subtitle) | |
st.text('Compute summary...') | |
# inputs = tokenizer( | |
# [subtitle], | |
# max_length=600, | |
# padding="max_length", | |
# truncation=True, | |
# return_tensors="pt", | |
# )["input_ids"] | |
# # inputs = tokenizer(subtitle, return_tensors="pt").input_ids | |
# outputs = model.generate(inputs, max_new_tokens=100, do_sample=False) | |
# summary = tokenizer.decode(outputs[0], skip_special_tokens=True) | |
translator = pipeline("summarization", model=m_name, | |
tokenizer=m_name, max_length=100, device=0 | |
) | |
st.subheader('Summary') | |
st.text(translator(subtitle)) | |
else: | |
st.write('Subtitles are disabled for this video') | |
else: | |
st.write('Video clip is not detected') | |