教程出错，声码器训练时batch_size设置错误

经我个人测试，我认为声码器训练时如果出现显存不足错误，报错退出后，应该修改vocoder\hifigan\config_16k_.json 文件中的batch_size，因为

vocoder_train.py里这么写的：

parser.add_argument("--config", type=str, default="vocoder/hifigan/config_16k_.json")

显存不足报错退出后，修改vocoder\wavernn\hparams.py里面的
voc_batch_size = 16
应该是没效果的

Read vocoder_train.py and compare its default --config path with vocoder/hifigan/config_16k_.json and vocoder/wavernn/hparams.py. Update the tutorial so the out-of-memory guidance points to the setting used by the training command, then verify that the documented file and parameter match the command’s default configuration.

Written by the indexing model from the issue text.