Update app.py

app.py

@@ -9,7 +9,7 @@ token = os.getenv("HF_TOKEN")
 login(token=token)
 
 # Whisper Model Optimization
-model = "openai/whisper-small"
+model = "openai/whisper-tiny"
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 
 processor = AutoProcessor.from_pretrained(model)
@@ -24,7 +24,7 @@ transcriber = pipeline(
 )
 
 # LLaMA Model Optimization
-LLAMA = "meta-llama/Meta-Llama-3.1-8B-Instruct"
+LLAMA = "meta-llama/Llama-3.2-3B-Instruct"
 llama_quant_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_use_double_quant=True,
@@ -47,7 +47,8 @@ def process_audio(audio_file):
 
     # Transcribe audio
     transcript = transcriber(audio_file)["text"]
-    
+    del transcriber 
+    del processor
     # Generate meeting minutes
     system_message = "You are an assistant that produces minutes of meetings from transcripts, with summary, key discussion points, takeaways and action items with owners, in markdown."
     user_prompt = f"Below is an extract transcript of a Denver council meeting. Please write minutes in markdown, including a summary with attendees, location and date; discussion points; takeaways; and action items with owners.\n{transcript}"