diff --git a/README.md b/README.md
index e2ec465..fb9c8f0 100644
--- a/README.md
+++ b/README.md
@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 12.62
+         value: 12.90
 ---
 
 # Wav2Vec2-Large-XLSR-53-German
@@ -152,7 +152,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8) # batch_size=8 -
 
 # non-chunked version:
 # print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
-# WER: 12.615308
+# WER: 12.900291 
 
 # Chunked version, see https://discuss.huggingface.co/t/spanish-asr-fine-tuning-wav2vec2/4586/5:
 import jiwer
@@ -176,7 +176,7 @@ print("Total (chunk_size=1000), WER: {:2f}".format(100 * chunked_wer(result["pre
 # Total (chunk=1000), WER: 12.768981
 ```
 
-**Test Result**: 12.62 %
+**Test Result**: WER: 12.90 %
 
 
 ## Training