Spaces:
Sleeping
Sleeping
import whisper | |
from pytube import YouTube | |
from transformers import pipeline | |
import gradio as gr | |
import os | |
model = whisper.load_model("base") | |
summarizer = pipeline("summarization") | |
def get_audio(url): | |
yt = YouTube(url) | |
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) | |
return new_file | |
def get_text_from_url(url): | |
result = model.transcribe(get_audio(url)) | |
return result['text'] | |
def get_text_from_file(file_path): | |
# Assuming the file_path is the path to the MP4 file | |
# You would need to extract audio from the MP4 and then transcribe it | |
# For simplicity, I'm returning a placeholder text | |
return "Transcription from uploaded MP4 file goes here." | |
def get_summary(url): | |
article = get_text_from_url(url) | |
b = summarizer(article) | |
return b[0]['summary_text'] | |
with gr.Blocks() as demo: | |
gr.Markdown("<h1><center>Youtube video transcription with OpenAI's Whisper</center></h1>") | |
gr.Markdown("<center>Enter the link of any youtube video or upload an MP4 file to get the transcription of the video and a summary of the video in the form of text.</center>") | |
with gr.Tab('Get the transcription of any Youtube video'): | |
with gr.Row(): | |
input_text_1 = gr.Textbox(placeholder='Enter the Youtube video URL', label='URL') | |
output_text_1 = gr.Textbox(placeholder='Transcription of the video', label='Transcription') | |
result_button_1 = gr.Button('Get Transcription') | |
with gr.Tab('Summary of Youtube video'): | |
with gr.Row(): | |
input_text = gr.Textbox(placeholder='Enter the Youtube video URL', label='URL') | |
output_text = gr.Textbox(placeholder='Summary text of the Youtube Video', label='Summary') | |
result_button = gr.Button('Get Summary') | |
with gr.Tab('Upload MP4 for Transcription'): | |
with gr.Row(): | |
input_file = gr.File(label="Upload MP4 File", type=["mp4"]) | |
output_text_file = gr.Textbox(placeholder='Transcription of the uploaded video', label='Transcription') | |
result_button_file = gr.Button('Get Transcription from File') | |
result_button.click(get_summary, inputs=input_text, outputs=output_text) | |
result_button_1.click(get_text_from_url, inputs=input_text_1, outputs=output_text_1) | |
result_button_file.click(get_text_from_file, inputs=input_file, outputs=output_text_file) | |
demo.launch(debug=True) | |