Update README.md

README.md

@@ -93,6 +93,6 @@ print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"],
 **Test Result**: 25.09 % 
 
 ## Training
-The Common Voice `train` and `validation` datasets were used for training for 4000 steps due to running out of GPU. The results are based on the 4000 steps checkpoint. There is a good chance that full training will lead to better results.
+The Common Voice `train` and `validation` datasets were used for training for 4000 steps due to GPU timeout. The results are based on the 4000 steps checkpoint. There is a good chance that full training will lead to better results.
 
 The colab notebook used can be found [here](https://colab.research.google.com/drive/1nbqvVwS8DTNrCzzh3vgrN55qxgoqbita?usp=sharing) and the evaluation can be found [here](https://colab.research.google.com/drive/18pCWBwNNUMUYV1FiqT_0EsTbCfwwe7ms?usp=sharing).