birgermoell
/

swedish-common-voice-vox-voxpopuli

Automatic Speech Recognition Transformers PyTorch JAX

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

Model card Files Files and versions Community

birgermoell commited on Jul 1, 2021

Commit

6842e86

•

1 Parent(s): eced13c

Update README.md

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -111,9 +111,8 @@ def evaluate(batch):
     pred_ids = torch.argmax(logits, dim=-1)
 \\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
-\\\\\\\\\\\\\\\\\\\\WER: 36.951816
 **Test Result**:
 WER: 22.684600

     pred_ids = torch.argmax(logits, dim=-1)
 \\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\tbatch["pred_strings"] = processor.batch_decode(pred_ids)
+\\\\\\\\\\\\\\\\\\\\
+```
 **Test Result**:
 WER: 22.684600