facebook
/

s2t-small-librispeech-asr

Automatic Speech Recognition

hf-asr-leaderboard

Eval Results (legacy)

Model card Files Files and versions

sanchit-gandhi commited on Dec 7, 2022

Commit

2e3b22f

·

1 Parent(s): bb4003f

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -128,12 +128,12 @@ def map_to_pred(batch):
     attention_mask = features.attention_mask.to("cuda")
     gen_tokens = model.generate(input_features=input_features, attention_mask=attention_mask)
-    batch["transcription"] = processor.batch_decode(gen_tokens, skip_special_tokens=True)
     return batch
 result = librispeech_eval.map(map_to_pred, remove_columns=["audio"])
-print("WER:", wer(predictions=result["transcription"], references=result["text"]))
 ```
 *Result (WER)*:

     attention_mask = features.attention_mask.to("cuda")
     gen_tokens = model.generate(input_features=input_features, attention_mask=attention_mask)
+    batch["transcription"] = processor.batch_decode(gen_tokens, skip_special_tokens=True)[0]
     return batch
 result = librispeech_eval.map(map_to_pred, remove_columns=["audio"])
+print("WER:", wer.compute(predictions=result["transcription"], references=result["text"]))
 ```
 *Result (WER)*: