Create app.py

app.py

@@ -0,0 +1,26 @@
+from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
+import gradio as gr
+
+# Load the model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("machinelearningzuu/youtube-content-summarization")
+model = AutoModelForSeq2SeqLM.from_pretrained("machinelearningzuu/youtube-content-summarization")
+
+# Define a function for summarization
+def summarize_youtube_content(input_text):
+    # Use the pipeline for summarization
+    summarizer = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
+    summary = summarizer(input_text, max_length=150, min_length=30, do_sample=False)
+    return summary[0]['generated_text']
+
+# Create a Gradio interface
+interface = gr.Interface(
+    fn=summarize_youtube_content,
+    inputs=gr.Textbox(lines=10, placeholder="Paste YouTube transcript here..."),
+    outputs=gr.Textbox(lines=5, label="Summarized Content"),
+    title="YouTube Content Summarizer",
+    description="Paste the transcript of a YouTube video to generate a concise summary.",
+)
+
+# Launch the Gradio app
+if __name__ == "__main__":
+    interface.launch()