Update app.py

app.py

@@ -4,6 +4,7 @@ import torch
 
 import gradio as gr
 import pytube as pt
+import spaces
 from transformers import pipeline
 from huggingface_hub import model_info
 
@@ -13,6 +14,7 @@ lang = "fi"
 share = (os.environ.get("SHARE", "False")[0].lower() in "ty1") or None
 auth_token = os.environ.get("AUTH_TOKEN") or True
 device = 0 if torch.cuda.is_available() else "cpu"
+print("Using device: {device}")
 pipe = pipeline(
     task="automatic-speech-recognition",
     model=MODEL_NAME,
@@ -23,6 +25,7 @@ pipe = pipeline(
 
 pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")
 
+@spaces.GPU(duration=120)
 def transcribe(microphone, file_upload):
     warn_output = ""
     if (microphone is not None) and (file_upload is not None):