Duplicate from BilalSardar/yt-summarizer

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.ckpt 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
+*.mlmodel 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
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.safetensors 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 +1,13 @@
+---
+title: Yt Summarizer
+emoji: 📚
+colorFrom: yellow
+colorTo: pink
+sdk: gradio
+sdk_version: 3.16.2
+app_file: app.py
+pinned: false
+duplicated_from: BilalSardar/yt-summarizer
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,18 @@
+import gradio as gr
+from summarize import Summarizer
+
+interface = gr.Interface(fn = Summarizer,
+                        inputs = [gr.inputs.Textbox(lines=2, 
+                                                    placeholder="Enter your link...",
+                                                    label='YouTube Video Link'),
+                                  gr.inputs.Radio(["mT5", "BART"], type="value", label='Model')],
+                        outputs = [gr.outputs.Textbox(
+                                                      label="Summary")],
+                         
+                        title = "Youtube Video Summarizer",
+                        examples = [
+                                   ['https://www.youtube.com/watch?v=WSbgixdC9g8', 'BART']
+                                   ],
+                        enable_queue=True)
+
+interface.launch(debug=True) 

requirements.txt

@@ -0,0 +1,5 @@
+torch
+transformers
+sentencepiece
+youtube-transcript-api
+

summarize.py

@@ -0,0 +1,44 @@
+import traceback
+import sys
+
+from youtube_transcript_api import YouTubeTranscriptApi
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+def Summarizer(link, model):
+  
+  video_id = link.split("=")[1]
+
+  try:
+    transcript = YouTubeTranscriptApi.get_transcript(video_id)
+    FinalTranscript = ' '.join([i['text'] for i in transcript])
+    
+    if model == "Pegasus":
+      checkpoint = "google/pegasus-large"
+    elif model == "mT5":
+      checkpoint = "csebuetnlp/mT5_multilingual_XLSum"
+    elif model == "BART":
+      checkpoint = "sshleifer/distilbart-cnn-12-6"
+      
+    tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+    model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
+
+
+    inputs = tokenizer(FinalTranscript, 
+                    max_length=1024, 
+                    truncation=True,
+                    return_tensors="pt")
+    
+    summary_ids = model.generate(inputs["input_ids"])
+    summary = tokenizer.batch_decode(summary_ids, 
+                                  skip_special_tokens=True, 
+                                  clean_up_tokenization_spaces=False)
+    
+
+    return summary[0]
+    
+
+  except Exception:
+    print(traceback.format_exc())
+    # or
+    print(sys.exc_info()[2])
+