处理数据、数据归一化都顺利进行，在训练数据时发生报错：

python examples/tacotron2/train_tacotron2.py --train-dir dump/train/ \
  --dev-dir dump/valid/ \
  --outdir examples/tacotron2/exp/train.tacotron2.baker.v1/ \
  --config examples/tacotron2/conf/tacotron2.baker.v1.yaml \
  --use-norm 1 \
  --mixed_precision 0 \
  --resume examples/tacotron2/exp/train.tacotron2.baker.v1/checkpoints/

报错信息：

Traceback (most recent call last):
  File "examples/tacotron2/train_tacotron2.py", line 488, in <module>
    main()
  File "examples/tacotron2/train_tacotron2.py", line 436, in main
    tacotron2 = TFTacotron2(config=tacotron_config, training=True, name="tacotron2")
  File "/root/anaconda3/envs/tts/lib/python3.6/site-packages/tensorflow_tts/models/tacotron2.py", line 746, in __init__
    super().__init__(self, **kwargs)
  File "/root/anaconda3/envs/tts/lib/python3.6/site-packages/tensorflow/python/training/tracking/base.py", line 457, in _method_wrapper
    result = method(self, *args, **kwargs)
  File "/root/anaconda3/envs/tts/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 262, in __init__
    'name', 'autocast'})
  File "/root/anaconda3/envs/tts/lib/python3.6/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 778, in validate_kwargs
    raise TypeError(error_message, kwarg)
TypeError: ('Keyword argument not understood:', 'training')

[nltk_data] Error loading averaged_perceptron_tagger: <urlopen error
[nltk_data]     [Errno 99] Cannot assign requested address>
[nltk_data] Error loading cmudict: <urlopen error [Errno 99] Cannot
[nltk_data]     assign requested address>

不知道有没有影响？

[nltk_data] Error loading averaged_perceptron_tagger: <urlopen error
[nltk_data]     [Errno 99] Cannot assign requested address>
[nltk_data] Error loading cmudict: <urlopen error [Errno 99] Cannot
[nltk_data]     assign requested address>

但训练时，还是有这个错误：

Traceback (most recent call last):
  File "examples/tacotron2/train_tacotron2.py", line 488, in <module>
    main()
  File "examples/tacotron2/train_tacotron2.py", line 436, in main
    tacotron2 = TFTacotron2(config=tacotron_config, training=True, name="tacotron2")
  File "/root/anaconda3/envs/tts/lib/python3.6/site-packages/tensorflow_tts/models/tacotron2.py", line 746, in __init__
    super().__init__(self, **kwargs)
  File "/root/anaconda3/envs/tts/lib/python3.6/site-packages/tensorflow/python/training/tracking/base.py", line 457, in _method_wrapper
    result = method(self, *args, **kwargs)
  File "/root/anaconda3/envs/tts/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 262, in __init__
    'name', 'autocast'})
  File "/root/anaconda3/envs/tts/lib/python3.6/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 778, in validate_kwargs
    raise TypeError(error_message, kwarg)
TypeError: ('Keyword argument not understood:', 'training')