Update app.py

app.py

@@ -4,8 +4,14 @@ import gradio as gr
 import numpy as np
 from groq import Groq
 from transformers import pipeline
+from transformers.utils import is_flash_attn_2_available
 
-transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
+transcriber = pipeline("automatic-speech-recognition",
+                       model="openai/whisper-large-v3",
+                       torch_dtype=torch.float16,
+                       device="cuda:0",
+                       model_kwargs={"attn_implementation": "flash_attention_2"} if is_flash_attn_2_available() else {"attn_implementation": "sdpa"},
+                      )
 
 groq_client = Groq(api_key=os.getenv('GROQ_API_KEY'))