Update README.md

README.md

@@ -21,10 +21,12 @@ 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
+logits = model(input_values).logits
 pred_ids = torch.argmax(logits, dim=-1)
 
 # dummy loss
-dummy_labels = torch.zeros((logits.shape[0], logits.shape[0] - 10))
-loss = model(input_ids, labels=dummy_labels).loss
+dummy_labels = pred_ids.clone()
+dummy_labels[dummy_labels == model.config.pad_token_id] = 1  # can't have CTC blank token in label
+dummy_labels = dummy_labels[:, -(dummy_labels.shape[1] // 4):] # make sure labels are shorter to avoid "inf" loss (can still happen though...)
+loss = model(input_values, labels=dummy_labels).loss
 ```