diff --git a/paddlespeech/t2s/models/fastspeech2/fastspeech2.py b/paddlespeech/t2s/models/fastspeech2/fastspeech2.py
index 295a2e4b3b8003af26310ee612337ccf8518491d..405ad957d478621c15ddc3185bd31d459006c140 100644
--- a/paddlespeech/t2s/models/fastspeech2/fastspeech2.py
+++ b/paddlespeech/t2s/models/fastspeech2/fastspeech2.py
@@ -940,8 +940,6 @@ class StyleFastSpeech2Inference(FastSpeech2Inference):
         Tensor
             Output sequence of features (L, odim).
         """
-        if spk_id:
-            spk_id = paddle.to_tensor(spk_id)
         normalized_mel, d_outs, p_outs, e_outs = self.acoustic_model.inference(
             text,
             durations=None,