Training Tacotron2
I am trying to train Tacotron2 with LJSpeech dataset which is already available, I did not change any thing, after running the following command
cd recipes/LJSpeech/TTS/tacotron2/
python train.py --device=cuda:0 --max_grad_norm=1.0 --data_folder=/your_folder/LJSpeech-1.1 hparams/train.yaml
I am getting the following error:
static_keys = list(self.data[self.data_ids[0]].keys())
IndexError: list index out of range
Can anyone help me to fix it?
Hi @affrasiabzafar , do you still have this problem? I can not reproduce this error, it seems that something went wrong during the preparation. Guess there was nothing in your json files.
Maybe check your data and the preparation process.
Hi,
@yingzhi
Thanks for responding. No I don't have this error anymore. I just pulled the repo again and tried it.... it got fixed.