File size: 3,028 Bytes
3331823 f4bd310 3331823 f4bd310 3331823 f4bd310 3331823 f4bd310 3331823 f4bd310 3331823 f4bd310 |
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 |
import whisper
import yt_dlp
import gradio as gr
import os
import re
model = whisper.load_model("base")
def get_audio(url):
try:
ydl_opts = {
'format': 'bestaudio/best',
'outtmpl': '%(id)s.%(ext)s',
'noplaylist': True,
'quiet': True
}
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
info = ydl.extract_info(url, download=True)
audio_file = os.path.join(ydl.outtmpl % info)
return audio_file
except Exception as e:
raise gr.Error(f"Exception: {e}")
def get_text(url):
try:
if url != '':
audio_file = get_audio(url)
result = model.transcribe(audio_file)
return result['text'].strip()
else:
return "Please enter a YouTube video URL."
except Exception as e:
raise gr.Error(f"Exception: {e}")
def get_summary(article):
try:
first_sentences = ' '.join(re.split(r'(?<=[.:;])\s', article)[:5])
# Assuming you have a summarizer pipeline set up
# b = summarizer(first_sentences, min_length = 20, max_length = 120, do_sample = False)
# b = b[0]['summary_text'].replace(' .', '.').strip()
# return b
# Since no summarizer is defined, return the first sentences for now
return first_sentences
except Exception as e:
raise gr.Error(f"Exception: {e}")
with gr.Blocks() as demo:
gr.Markdown("<h1><center>Free Fast YouTube URL Video-to-Text using <a href=https://openai.com/blog/whisper/ target=_blank>OpenAI's Whisper</a> Model</center></h1>")
#gr.Markdown("<center>Enter the link of any YouTube video to generate a text transcript of the video and then create a summary of the video transcript.</center>")
gr.Markdown("<center>Enter the link of any YouTube video to generate a text transcript of the video.</center>")
gr.Markdown("<center><b>'Whisper is a neural net that approaches human level robustness and accuracy on English speech recognition.'</b></center>")
gr.Markdown("<center>Transcription takes 5-10 seconds per minute of the video (bad audio/hard accents slow it down a bit). #patience<br />If you have time while waiting, check out my <a href=https://www.artificial-intelligence.blog target=_blank>AI blog</a> (opens in new tab).</center>")
input_text_url = gr.Textbox(placeholder='Youtube video URL', label='URL')
result_button_transcribe = gr.Button('1. Transcribe')
output_text_transcribe = gr.Textbox(placeholder='Transcript of the YouTube video.', label='Transcript')
#result_button_summary = gr.Button('2. Create Summary')
#output_text_summary = gr.Textbox(placeholder='Summary of the YouTube video transcript.', label='Summary')
result_button_transcribe.click(get_text, inputs = input_text_url, outputs = output_text_transcribe)
#result_button_summary.click(get_summary, inputs = output_text_transcribe, outputs = output_text_summary)
demo.queue(default_enabled = True).launch(debug = True) |