Upload 2 files

app.py

@@ -0,0 +1,58 @@
+import whisper
+from pytube import YouTube
+from transformers import pipeline
+import gradio as gr
+import os
+import re
+
+model = whisper.load_model("base")
+# model = pipeline(model="AlexMo/FIFA_WC22_WINNER_LANGUAGE_MODEL")
+summarizer = pipeline("summarization")
+
+
+def getAudio(url):
+    link = YouTube(url)
+    video = link.streams.filter(only_audio=True).first()
+    file = video.download(output_path=".")
+    base, ext = os.path.splitext(file)
+    file_ext = base + '.mp3'
+    os.rename(file, file_ext)
+    return file_ext
+
+
+def getText(url):
+    if url != '':
+        output_text_transcribe = ''
+    res = model.transcribe(getAudio(url))
+    return res['text'].strip()
+
+
+def getSummary(article):
+    header = ' '.join(re.split(r'(?<=[.:;])\s', article)[:5])
+    b = summarizer(header, min_length=15, max_length=120, do_sample=False)
+    b = b[0]['summary_text'].replace(' .', '.').strip()
+
+    return b
+
+
+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><b>'Whisper is a neural net that approaches human level robustness and accuracy on English speech recognition.'</b></center>")
+    gr.Markdown(
+        "<center>Generating the transcript takes 5-10 seconds per minute of the video</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(getText, inputs=input_text_url, outputs=output_text_transcribe)
+    result_button_summary.click(getSummary, inputs=output_text_transcribe, outputs=output_text_summary)
+
+demo.launch(debug=True)

requirements.txt

@@ -0,0 +1,12 @@
+hopsworks
+joblib
+scikit-learn
+seaborn
+dataframe-image
+modal-client
+gradio
+pytube
+whisper
+transformers
+re
+os