Update README.md

README.md

@@ -107,18 +107,7 @@ The following hyperparameters were used during training:
 - num_train_epochs: 10
 - lr_scheduler_type: linear
 
-### Test results
-The final model was evaluated as follows:
-
-On reazonspeech(tiny):
-- WER: 40.519700%
-- CER: 23.220979%
-
-On common_voice_11_0:
-- WER: 22.705487%
-- CER: 9.399390%
-
-### How to use the model
+### How to evaluate the model
 
 ```python
 from transformers import HubertForCTC, Wav2Vec2Processor
@@ -201,6 +190,18 @@ cer_result = cer.compute(predictions=result["pred_strings"], references=result["
 print("WER: {:2f}%".format(100 * wer_result))
 print("CER: {:2f}%".format(100 * cer_result))
 ```
+
+### Test results
+The final model was evaluated as follows:
+
+On reazonspeech(tiny):
+- WER: 40.519700%
+- CER: 23.220979%
+
+On common_voice_11_0:
+- WER: 22.705487%
+- CER: 9.399390%
+
 ### Framework versions
 
 - Transformers 4.39.1