Change the cache_dir

app/main.py

@@ -4,17 +4,18 @@ from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 
 app = FastAPI()
 
-device = "cuda:0" if torch.cuda.is_available() else "cpu"
+device = "cuda" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
 model_id = "openai/whisper-large-v3"
 
 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,
+    cache_dir="./"
 )
 model.to(device)
 
-processor = AutoProcessor.from_pretrained(model_id)
+processor = AutoProcessor.from_pretrained(model_id, cache_dir="./")
 
 pipe = pipeline(
     "automatic-speech-recognition",