cosyvoice1:使用代码执行跨语种复刻时报错

[FaderYin]

代码

# 使用的就是提供的示例代码
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M') # or change to 

# cross_lingual usage
prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k)):
    waveform = torch.tensor(j['tts_speech']) if not isinstance(j['tts_speech'], torch.Tensor) else j['tts_speech']
    torchaudio.save('cross_lingual_{}.wav'.format(i), waveform, cosyvoice.sample_rate)

报错

发生异常: TypeError
string indices must be integers
  File "D:\Project\github\TTS\cosyvoice\CosyVoice\demo2.py", line 20, in <module>
    waveform = torch.tensor(j['tts_speech']) if not isinstance(j['tts_speech'], torch.Tensor) else j['tts_speech']
TypeError: string indices must be integers

[aluminumbox]

本地验证了一下并没有发现问题