Update eval.py

eval.py

@@ -4,6 +4,7 @@ import re
 import unicodedata
 from typing import Dict
 
+import torch
 from datasets import Audio, Dataset, load_dataset, load_metric
 
 from transformers import AutoFeatureExtractor, pipeline
@@ -90,7 +91,11 @@ def main(args):
     dataset = dataset.cast_column("audio", Audio(sampling_rate=sampling_rate))
 
     # load eval pipeline
-    asr = pipeline("automatic-speech-recognition", model=args.model_id, device=0)
+    if args.device is None:
+        args.device = 0 if torch.cuda.is_available() else -1
+    asr = pipeline(
+        "automatic-speech-recognition", model=args.model_id, device=args.device
+    )
 
     # map function to decode audio
     def map_to_pred(batch):
@@ -153,6 +158,12 @@ if __name__ == "__main__":
         action="store_true",
         help="If defined, write outputs to log file for analysis.",
     )
+    parser.add_argument(
+        "--device",
+        type=int,
+        default=None,
+        help="The device to run the pipeline on. -1 for CPU (default), 0 for the first GPU and so on.",
+    )
     args = parser.parse_args()
 
     main(args)