changed attention implementation to "sdpa" from default "eager"

handler.py

@@ -13,7 +13,9 @@ class EndpointHandler():
         model_id = "openai/whisper-large-v3-turbo"
 
         model = AutoModelForSpeechSeq2Seq.from_pretrained(
-            model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
+            model_id, torch_dtype=torch_dtype,
+            low_cpu_mem_usage=True, use_safetensors=True,
+            attn_implementation="sdpa"
         )
         model.to(device)