[TTS]在使用中英文混合模型fastspeech2_male 不会报错，而fastspeech2_mix时一直报错！

[FavoriteStar]

具体代码为： `import paddle from paddlespeech.cli.tts import TTSExecutor

def tts(text,output): #paddle.device.set_device('gpu:0') tts_executor = TTSExecutor() wav_file = tts_executor( text=text, output=output, am='fastspeech2_mix', am_config=None, am_ckpt=None, am_stat=None, spk_id=0, phones_dict=None, tones_dict=None, speaker_dict=None, voc='hifigan_aishell3', voc_config=None, voc_ckpt=None, voc_stat=None, lang='mix', device=paddle.get_device())

if name == "main": text = "你好我的名字是Peter，你好" path = "test中英文混合.wav" tts(text, path)`

其他的voc都尝试了，只要是mix就会报这个错误

报错信息为： Traceback (most recent call last): File "/home/hsy/test中英.py", line 30, in tts(text, path) File "/home/hsy/test中英.py", line 7, in tts wav_file = tts_executor( File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/paddlespeech/cli/utils.py", line 328, in _warpper return executor_func(self, *args, **kwargs) File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/paddlespeech/cli/tts/infer.py", line 710, in call self.infer(text=text, lang=lang, am=am, spk_id=spk_id) File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/decorator.py", line 232, in fun return caller(func, *(extras + args), **kw) File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/paddle/fluid/dygraph/base.py", line 347, in _decorate_function return func(*args, **kwargs) File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/paddlespeech/cli/tts/infer.py", line 493, in infer mel = self.am_inference( File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/paddle/nn/layer/layers.py", line 1254, in call return self.forward(*inputs, **kwargs) File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/paddlespeech/t2s/models/fastspeech2/fastspeech2.py", line 920, in forward normalized_mel, d_outs, p_outs, e_outs = self.acoustic_model.inference( File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/paddlespeech/t2s/models/fastspeech2/fastspeech2.py", line 810, in inference _, outs, d_outs, p_outs, e_outs, _ = self._forward( File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/paddlespeech/t2s/models/fastspeech2/fastspeech2.py", line 618, in _forward hs = self._integrate_with_spk_embed(hs, spk_emb) File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/paddlespeech/t2s/models/fastspeech2/fastspeech2.py", line 840, in _integrate_with_spk_embed spk_emb = F.normalize(spk_emb).unsqueeze(1).expand( File "/home/Lyx/Software/anaconda3/envs/langchain/lib/python3.8/site-packages/paddle/nn/functional/norm.py", line 82, in normalize out = _C_ops.p_norm(x, float(p), axis, epsilon, True, False) ValueError: (InvalidArgument) Attr(axis) value should be in range [-R, R-1], R is the rank of Input(X). But received axis: 1, R: 1. Current Input(X)'s shape is=[256]. [Hint: Expected axis < x_rank, but received axis:1 >= x_rank:1.] (at ../paddle/phi/infermeta/unary.cc:2763)

请问该怎么办呢？

[whtwhtw]

加入参数am='fastspeech2_mix'就会出现楼主描述的问题， am=其它-zh的参数就不会出现这个问题，但是识别不了英文

[sujianwei1]

paddlespeech tts --am fastspeech2_canton --voc pwgan_aishell3 --input "各个国家有各个国家嘅国歌" --lang canton --spk_id 10 我用的官方样例，也出现这个报错

[zqkou]

  tts = TTSExecutor()
  tts(text="你好我的名字是Peter，你好", output="output.wav", am='fastspeech2_mix', lang='mix')

遇到同样错误