Update README.md

README.md

@@ -4091,10 +4091,10 @@ xeus_model, xeus_train_args = SSLTask.build_model_from_file(
 
 wavs, sampling_rate = sf.read('/path/to/audio.wav') # sampling rate should be 16000
 wav_lengths = torch.LongTensor([len(wav) for wav in [wavs]]).to(device)
-wavs = pad_sequence([wavs], batch_first=True).to(device)
+wavs = pad_sequence(torch.Tensor([wavs]), batch_first=True).to(device) 
 
 # we recommend use_mask=True during fine-tuning
-feats = xeus_model.encode(wavs, wav_lengths, use_mask=False, use_final_output=False)[0][-1] # take the output of the last layer
+feats = xeus_model.encode(wavs, wav_lengths, use_mask=False, use_final_output=False)[0][-1] # take the output of the last layer -> batch_size x seq_len x hdim
 ```
 
 With Flash Attention: