Spaces:
Runtime error
Runtime error
File size: 1,866 Bytes
c1f076a dec5a5d c1f076a dec5a5d 04a0f7f dec5a5d c1f076a dec5a5d |
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 |
import gradio as gr
from pytube import YouTube
import subprocess
import torch
from huggingsound import SpeechRecognitionModel
import librosa
import soundfile as sf
from transformers import pipeline
def summarize_video(youtube_link):
# Download YouTube video's audio
yt = YouTube(youtube_link)
yt.streams.filter(only_audio=True, file_extension='mp4').first().download(filename='ytaudio.mp4')
# Convert to WAV format
subprocess.run(['ffmpeg', '-i', 'ytaudio.mp4', '-acodec', 'pcm_s16le', '-ar', '16000', 'ytaudio.wav'], check=True)
# Initialize speech recognition model
device = "cuda" if torch.cuda.is_available() else "cpu"
model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-english", device=device)
# Process audio file and transcribe
input_file = 'ytaudio.wav'
stream = librosa.stream(input_file, block_length=30, frame_length=16000, hop_length=16000)
full_transcript = ''
for i, speech in enumerate(stream):
sf.write(f'{i}.wav', speech, 16000)
transcription = model.transcribe([f'{i}.wav'])
full_transcript += ' '.join([item['transcription'] for item in transcription])
# Summarize the transcript
summarizer = pipeline('summarization')
summarized_text = summarizer(full_transcript, max_length=130, min_length=30, do_sample=False)
return summarized_text[0]['summary_text']
# Set up the Gradio interface
iface = gr.Interface(fn=summarize_video,
inputs=gr.inputs.Textbox(lines=2, placeholder="Enter YouTube Video Link Here..."),
outputs="text",
title="YouTube Video Text Summarizer",
description="This tool summarizes the text extracted from a given YouTube video. Please enter the video link below.")
if __name__ == "__main__":
iface.launch()
|