Use zero GPU

app.py

@@ -1,3 +1,4 @@
+import spaces
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 from transformers.utils import is_flash_attn_2_available, is_torch_sdpa_available
 from transformers.pipelines.audio_utils import ffmpeg_read
@@ -52,6 +53,7 @@ distil_pipe = pipeline(
 distil_pipe_forward = distil_pipe._forward
 
 
+@spaces.GPU
 def transcribe(inputs):
     if inputs is None:
         raise gr.Error("No audio file submitted! Please record or upload an audio file before submitting your request.")