marcel
/

wav2vec2-large-xlsr-53-german

Automatic Speech Recognition Transformers PyTorch JAX

German wav2vec2 audio speech xlsr-fine-tuning-week Eval Results Inference Endpoints

Model card Files Files and versions Community

marcel commited on Mar 28, 2021

Commit

32d34ee

•

1 Parent(s): e626da1

WER

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 16.22
 ---
 # Wav2Vec2-Large-XLSR-53-German
@@ -140,7 +140,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
-**Test Result**: 16.22 %
 ## Training

     metrics:
        - name: Test WER
          type: wer
+         value: 15.93
 ---
 # Wav2Vec2-Large-XLSR-53-German
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
+**Test Result**: 15.93 %
 ## Training