Duplicate from Geethanjali/YouTube_Transcript_Summarizer

Co-authored-by: Geethanjali B <Geethanjali@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.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
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet 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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: YouTube Transcript Summarizer
+emoji: 📚
+colorFrom: purple
+colorTo: purple
+sdk: gradio
+sdk_version: 3.0.24
+app_file: app.py
+pinned: false
+duplicated_from: Geethanjali/YouTube_Transcript_Summarizer
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,57 @@
+from transformers import pipeline
+from youtube_transcript_api import YouTubeTranscriptApi
+from keybert import KeyBERT
+import gradio as gr
+from keyphrase_vectorizers import KeyphraseCountVectorizer
+import requests
+from bs4 import BeautifulSoup
+
+def summarize_transcript(url):
+    video_id = url.split("=")[1]
+        
+    transcript = YouTubeTranscriptApi.get_transcript(video_id)
+
+    result = ""
+    for i in transcript:
+        result += ' ' + i['text']
+
+    summarizer = pipeline('summarization')
+    
+    num_iters = int(len(result)/1000)
+    summarized_text = []
+    for i in range(0, num_iters + 1):
+      start = 0
+      start = i * 1000
+      end = (i + 1) * 1000
+      out = summarizer(result[start:end])
+      out = out[0]
+      out = out['summary_text']
+      summarized_text.append(out)
+      summ = str(summarized_text)
+      print(summ)
+
+      #keywords
+      words = []
+      kw_model = KeyBERT()
+      keywords = kw_model.extract_keywords(summ)
+      w = kw_model.extract_keywords(summ, vectorizer=KeyphraseCountVectorizer())
+      for s in w:
+        words.append(s[0])
+
+      #tags
+      request = requests.get(url)
+      html = BeautifulSoup(request.content,"html.parser")
+      tags = html.find_all("meta",property = "og:video:tag")
+      lst = []
+      for tag in tags:
+        lst.append(tag['content'])
+    return (summ,words,lst)
+    
+gradio_ui = gr.Interface(fn = summarize_transcript,
+                  inputs = [gr.inputs.Textbox(label = "Enter the YouTube URL below:")],
+                  outputs = [gr.outputs.Textbox(label = "Transcript Summary"),gr.outputs.Textbox(label = "Keywords"),gr.outputs.Textbox(label = "Hash Tags")],
+                  title = "YouTube Transcript Summarizer",
+                  theme = "grass",
+                  description = "Here You can see the SUMMARY,KEYWORDS and HASHTAGS of the YouTube video you want to watch")
+               
+gradio_ui.launch(inline = False)

requirements.txt

@@ -0,0 +1,7 @@
+torch
+transformers
+youtube-transcript-api 
+keybert
+keyphrase_vectorizers 
+beautifulsoup4
+requests