diff --git a/paddlespeech/s2t/exps/deepspeech2/bin/test_wav.py b/paddlespeech/s2t/exps/deepspeech2/bin/test_wav.py
index d087405d..0b763684 100644
--- a/paddlespeech/s2t/exps/deepspeech2/bin/test_wav.py
+++ b/paddlespeech/s2t/exps/deepspeech2/bin/test_wav.py
@@ -75,7 +75,7 @@ class DeepSpeech2Tester_hub():
         feat = self.preprocessing(audio, **self.preprocess_args)
         logger.info(f"feat shape: {feat.shape}")
 
-        audio_len = paddle.to_tensor(feat.shape[0])
+        audio_len = paddle.to_tensor(feat.shape[0]).unsqueeze(0)
         audio = paddle.to_tensor(feat, dtype='float32').unsqueeze(axis=0)
 
         result_transcripts = self.compute_result_transcripts(
diff --git a/paddlespeech/s2t/exps/u2/bin/quant.py b/paddlespeech/s2t/exps/u2/bin/quant.py
index 73a9794f..72c64e46 100755
--- a/paddlespeech/s2t/exps/u2/bin/quant.py
+++ b/paddlespeech/s2t/exps/u2/bin/quant.py
@@ -75,7 +75,7 @@ class U2Infer():
                     feat = self.preprocessing(audio, **self.preprocess_args)
                     logger.info(f"feat shape: {feat.shape}")
 
-                    ilen = paddle.to_tensor(feat.shape[0])
+                    ilen = paddle.to_tensor(feat.shape[0]).unsqueeze(0)
                     xs = paddle.to_tensor(feat, dtype='float32').unsqueeze(0)
                     decode_config = self.config.decode
                     logger.info(f"decode cfg: {decode_config}")
diff --git a/paddlespeech/s2t/exps/u2/bin/test_wav.py b/paddlespeech/s2t/exps/u2/bin/test_wav.py
index a6228a12..0d1a3b3c 100644
--- a/paddlespeech/s2t/exps/u2/bin/test_wav.py
+++ b/paddlespeech/s2t/exps/u2/bin/test_wav.py
@@ -78,7 +78,7 @@ class U2Infer():
             if self.args.debug:
                 np.savetxt("feat.transform.txt", feat)
 
-            ilen = paddle.to_tensor(feat.shape[0])
+            ilen = paddle.to_tensor(feat.shape[0]).unsqueeze(0)
             xs = paddle.to_tensor(feat, dtype='float32').unsqueeze(0)
             decode_config = self.config.decode
             logger.info(f"decode cfg: {decode_config}")