facebook
/

wav2vec2-base-960h

Automatic Speech Recognition

hf-asr-leaderboard

Eval Results (legacy)

Model card Files Files and versions

patrickvonplaten commited on Feb 15, 2021

Commit

407ffc2

·

1 Parent(s): 829b55c

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -100,7 +100,7 @@ def map_to_pred(batch):
     batch["transcription"] = transcription
     return batch
-result = librispeech_eval.map(map_to_pred, batched=True, batch_size=16, remove_columns=["speech"])
 print("WER:", wer(result["text"], result["transcription"]))
 ```

     batch["transcription"] = transcription
     return batch
+result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["speech"])
 print("WER:", wer(result["text"], result["transcription"]))
 ```