alexcleu
/

wav2vec2-large-xlsr-polish

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

Alex Leu commited on Mar 26, 2021

Commit

2078734

•

1 Parent(s): 69df0ba

pol

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: xxx
 ---
 # wav2vec2-large-xlsr-polish
@@ -95,6 +95,6 @@ def evaluate(batch):
 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**:  xxx
 ## Training
 The Common Voice `train`, `validation` datasets were used for training.

     metrics:
        - name: Test WER
          type: wer
+         value: 24.846030
 ---
 # wav2vec2-large-xlsr-polish
 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**: 24.846030
 ## Training
 The Common Voice `train`, `validation` datasets were used for training.