openai
/

whisper-tiny

Automatic Speech Recognition

hf-asr-leaderboard

Model card Files Files and versions

ArthurZ HF Staff commited on Oct 10, 2022

Commit

b28761d

·

1 Parent(s): 6ee9f09

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -124,7 +124,7 @@ model-index:
     metrics:
     - name: Test WER
       type: wer
-      value: 7,639504403417127
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
@@ -138,7 +138,7 @@ model-index:
     metrics:
     - name: Test WER
       type: wer
-      value: 17,145720661094513
 pipeline_tag: automatic-speech-recognition
 license: apache-2.0
 ---
@@ -306,7 +306,7 @@ This code snippet shows how to evaluate **openai/whisper-tiny** on LibriSpeech's
 >>> result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["speech"])
 >>> print("WER:", wer(result["text"], result["transcription"]))
-0.07639504403417127
 ```

     metrics:
     - name: Test WER
       type: wer
+      value: 0.07547098647858638
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     metrics:
     - name: Test WER
       type: wer
+      value:  0.17145720661094513
 pipeline_tag: automatic-speech-recognition
 license: apache-2.0
 ---
 >>> result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["speech"])
 >>> print("WER:", wer(result["text"], result["transcription"]))
+0.07547098647858638
 ```