Duplicate from rajesh1729/youtube-video-transcription-with-whisper

Co-authored-by: Uppu Rajesh Kumar <rajesh1729@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Youtube Video Transcription With Whisper
+emoji: ⚡
+colorFrom: gray
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.3.1
+app_file: app.py
+pinned: false
+license: afl-3.0
+duplicated_from: rajesh1729/youtube-video-transcription-with-whisper
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,46 @@
+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)
+  a = new_file
+  return a
+
+def get_text(url):
+  result = model.transcribe(get_audio(url))
+  return result['text']
+
+def get_summary(url):
+  article = get_text(url)
+  b = summarizer(article)
+  b = b[0]['summary_text']
+  return b
+  
+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 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')
+
+  result_button.click(get_summary, inputs = input_text, outputs = output_text)
+  result_button_1.click(get_text, inputs = input_text_1, outputs = output_text_1)
+demo.launch(debug=True)

requirements.txt

@@ -0,0 +1,3 @@
+git+https://github.com/openai/whisper.git
+pytube
+transformers