diff --git a/funasr/models/sense_voice/model.py b/funasr/models/sense_voice/model.py
index 25e9fafd3..ba82091e9 100644
--- a/funasr/models/sense_voice/model.py
+++ b/funasr/models/sense_voice/model.py
@@ -555,7 +555,8 @@ class SenseVoiceEncoderSmall(nn.Module):
         ilens: torch.Tensor,
     ):
         """Embed positions in tensor."""
-        masks = sequence_mask(ilens, device=ilens.device)[:, None, :]
+        maxlen = xs_pad.shape[1]
+        masks = sequence_mask(ilens, maxlen = maxlen, device=ilens.device)[:, None, :]
 
         xs_pad *= self.output_size() ** 0.5