Create app.py

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import torch
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+# Load the GPT-2 model and tokenizer
+model_name = "openai-community/gpt2"
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+model = GPT2LMHeadModel.from_pretrained(model_name)
+
+def generate_transcript(input_text):
+    # Split the input text into smaller parts
+    sentences = input_text.split('. ')  # Simple split by sentences
+    new_transcripts = []
+
+    # Generate new transcript for each chunk
+    for sentence in sentences:
+        input_ids = tokenizer.encode(sentence, return_tensors='pt')
+
+        # Generate new text
+        with torch.no_grad():
+            output = model.generate(input_ids, max_length=50, num_return_sequences=1)
+
+        new_text = tokenizer.decode(output[0], skip_special_tokens=True)
+        new_transcripts.append(new_text)
+
+    # Combine all output to make the final transcript
+    final_transcript = '. '.join(new_transcripts)
+    
+    return final_transcript
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=generate_transcript,
+    inputs=gr.Textbox(lines=10, placeholder="Enter video transcript here..."),
+    outputs=gr.Textbox(),
+    title="Transcript Generator",
+    description="Enter a video transcript, and this app will generate a new, similar transcript using GPT-2."
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()