bardsai
/

whisper-medium-pl

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

kgawron commited on Dec 17, 2022

Commit

66edb8b

•

1 Parent(s): 719cb7f

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -22,9 +22,9 @@ model-index:
       split: test
       args: pl
     metrics:
-    - type: wer
-      value: 8.589801709229503
-      name: Wer
     - type: wer
       value: 8.85
       name: WER
@@ -113,7 +113,7 @@ When tested on diffrent polish ASR datasets (splits: test), this model achieves
 | Dataset           | WER   | WER unnormalized | CER   | MER   |
 |:-----------------:|:-----:|:----------------:|:-----:|:-----:|
-|common_voice_11_0  | ??.?? | ??.??            | ??.?? | ??.?? |
 ### Framework versions

       split: test
       args: pl
     metrics:
+    # - type: wer
+    #   value: 8.589801709229503
+    #   name: Wer
     - type: wer
       value: 8.85
       name: WER
 | Dataset           | WER   | WER unnormalized | CER   | MER   |
 |:-----------------:|:-----:|:----------------:|:-----:|:-----:|
+|common_voice_11_0  | 8.85 | 21.75            | 2.63 | 8.76 |
 ### Framework versions