未验证 提交 a232cd8b 编写于 作者: 小湉湉's avatar 小湉湉 提交者: GitHub

Update fastspeech2.py

上级 72986d05
...@@ -940,7 +940,8 @@ class StyleFastSpeech2Inference(FastSpeech2Inference): ...@@ -940,7 +940,8 @@ class StyleFastSpeech2Inference(FastSpeech2Inference):
Tensor Tensor
Output sequence of features (L, odim). Output sequence of features (L, odim).
""" """
spk_id = paddle.to_tensor(spk_id) if spk_id:
spk_id = paddle.to_tensor(spk_id)
normalized_mel, d_outs, p_outs, e_outs = self.acoustic_model.inference( normalized_mel, d_outs, p_outs, e_outs = self.acoustic_model.inference(
text, text,
durations=None, durations=None,
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册