Update app.py

app.py

@@ -3,6 +3,29 @@ from youtube_transcript_api import YouTubeTranscriptApi
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 import gradio as gr
 
+import os
+import uuid
+import joblib
+import json
+
+from huggingface_hub import CommitScheduler
+from pathlib import Path
+
+
+Prepare the logging functionality
+
+log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
+log_folder = log_file.parent
+
+scheduler = CommitScheduler(
+    repo_id="YouTubeSummarizer-log",
+    repo_type="dataset",
+    folder_path=log_folder,
+    path_in_repo="data",
+    every=2
+)
+
+
 # Load the Hugging Face model and tokenizer
 model_name = "sshleifer/distilbart-cnn-12-6"
 model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
@@ -26,6 +49,17 @@ def get_transcript(youtube_url):
     summary_ids = model.generate(inputs["input_ids"], num_beams=4, max_length=100, early_stopping=True)
     summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
 
+
+    with scheduler.lock:
+        with log_file.open("a") as f:
+            f.write(json.dumps(
+                {
+                    'YouTube URL': youtube_url,
+                    'Summary': summary
+                }
+            ))
+            f.write("\n")
+
     return summary
 
 # Create a Gradio interface
@@ -44,5 +78,7 @@ iface = gr.Interface(
     concurrency_limit=8
 )
 
+
+
 # Launch the Gradio interface
 iface.launch(share=False)