Spaces:
Sleeping
Sleeping
File size: 3,209 Bytes
52930d0 ce3a3a9 b2e37a3 ee8c3b8 7b1110c 5de25ba ee8c3b8 b2e37a3 ee8c3b8 b2e37a3 7b1110c b2e37a3 ee8c3b8 b2e37a3 ee8c3b8 b2e37a3 ee8c3b8 |
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 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
import streamlit as st
from pytube import YouTube
from moviepy.editor import AudioFileClip
import speech_recognition as sr
from transformers import pipeline
from pydub import AudioSegment, silence
import os
def download_and_extract_audio(youtube_link):
try:
yt = YouTube(youtube_link)
video = yt.streams.filter(only_audio=True).first()
out_file = video.download(output_path=".")
base, ext = os.path.splitext(out_file)
new_file = base + '.mp3'
os.rename(out_file, new_file)
# Convert MP3 to WAV using moviepy
audio_clip = AudioFileClip(new_file)
wav_file = base + '.wav'
audio_clip.write_audiofile(wav_file, codec='pcm_s16le') # codec for WAV format
audio_clip.close()
return wav_file
except Exception as e:
st.error(f"Error downloading and extracting audio: {e}")
return None
def transcribe_audio(audio_path):
try:
recognizer = sr.Recognizer()
audio = AudioSegment.from_wav(audio_path)
# Split the audio into non-silent chunks
audio_chunks = silence.split_on_silence(audio, min_silence_len=1000, silence_thresh=-40)
full_text = ""
for i, chunk in enumerate(audio_chunks):
chunk.export(f"/tmp/chunk{i}.wav", format="wav")
with sr.AudioFile(f"/tmp/chunk{i}.wav") as source:
audio_data = recognizer.record(source)
try:
text = recognizer.recognize_google(audio_data)
full_text += " " + text
except sr.UnknownValueError:
# Skip segments that the recognizer can't understand
continue
return full_text.strip()
except Exception as e:
st.error(f"Error transcribing audio: {e}")
return None
def summarize_text(text):
try:
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
summary = summarizer(text, max_length=130, min_length=30, do_sample=False)
return summary[0]['summary_text']
except Exception as e:
st.error(f"Error summarizing text: {e}")
return None
def main():
st.title("YouTube Video Summary")
youtube_link = st.text_input("Enter YouTube Video Link:")
if st.button("Summarize"):
if youtube_link:
with st.spinner('Downloading and extracting audio...'):
audio_path = download_and_extract_audio(youtube_link)
if audio_path is None:
return
with st.spinner('Transcribing audio to text...'):
transcription = transcribe_audio(audio_path)
if transcription is None:
return
with st.spinner('Summarizing transcription...'):
summary = summarize_text(transcription)
if summary is None:
return
st.subheader("Transcription:")
st.write(transcription)
st.subheader("Summary:")
st.write(summary)
else:
st.error("Please enter a valid YouTube video link.")
if __name__ == '__main__':
main()
|