Create app.py

app.py

@@ -0,0 +1,63 @@
+import gradio as gr
+import torch
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, TextStreamer
+
+# Whisper Model for Transcription
+WHISPER_MODEL = "openai/whisper-large-v3"
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+transcriber = pipeline(
+    task="automatic-speech-recognition",
+    model=WHISPER_MODEL,
+    chunk_length_s=30,
+    device=DEVICE,
+)
+
+# LLaMA Model for Generating Meeting Minutes
+LLAMA = "meta-llama/Llama-2-7b-chat-hf"  # Change to your preferred model
+quant_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_compute_dtype=torch.bfloat16,
+    bnb_4bit_quant_type="nf4"
+)
+
+# Load Model & Tokenizer
+tokenizer = AutoTokenizer.from_pretrained(LLAMA)
+tokenizer.pad_token = tokenizer.eos_token
+model = AutoModelForCausalLM.from_pretrained(LLAMA, device_map="auto", quantization_config=quant_config)
+
+# Function to Transcribe & Generate Minutes
+def process_audio(audio_file):
+    if audio_file is None:
+        return "Error: No audio provided!"
+
+    # Transcribe audio
+    transcript = transcriber(audio_file)["text"]
+    
+    # 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}"
+
+    messages = [
+        {"role": "system", "content": system_message},
+        {"role": "user", "content": user_prompt}
+    ]
+
+    inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(DEVICE)
+    streamer = TextStreamer(tokenizer)
+    outputs = model.generate(inputs, max_new_tokens=2000, streamer=streamer)
+
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=process_audio,
+    inputs=gr.Audio(sources=["upload", "microphone"], type="filepath"),
+    outputs="text",
+    title="Meeting Minutes Generator",
+    description="Upload or record an audio file to get structured meeting minutes in Markdown.",
+)
+
+# Launch App
+interface.launch()