patrickvonplaten
/

wav2vec2_tiny_random_robust

Automatic Speech Recognition

feature-extraction

Model card Files Files and versions

patrickvonplaten commited on May 3, 2021

Commit

21fcda0

·

1 Parent(s): ecec220

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ def load_audio(batch):
 ds = ds.map(load_audio)
-input_ids = torch.nn.utils.rnn.pad_sequence([torch.tensor(x[0]) for x in ds["samples"][:10]], batch_first=True)
 # forward
 logits = model(input_ids).logits

 ds = ds.map(load_audio)
+input_values = torch.nn.utils.rnn.pad_sequence([torch.tensor(x[0]) for x in ds["samples"][:10]], batch_first=True)
 # forward
 logits = model(input_ids).logits