Rachel ZHENG comments

Results 6 comments of


                                            Rachel ZHENG

keyerror when preprocess data

@liu-x-p Hi! I am also a Chinese student trying to run this repo and I am encountering some similar problems as you...TAT I wonder if you have successfully run this...

Issues with Audio Quality for Longer Text Inputs Using VCTK Pretrained Model

I've met the same problem while trying to apply the code to LibriTTS dataset. Whenever training or inferencing, the generated samples sound quite clear at the first 3 secs but...

Issues with Audio Quality for Longer Text Inputs Using VCTK Pretrained Model

@hungdinhxuan I didn't made any changes to the model configurations, but I made some minor changes while preprocessing the speech (though I don't think it would result in this phenomenon.)...

Issues with Audio Quality for Longer Text Inputs Using VCTK Pretrained Model

@hungdinhxuan It seems that the code provided in this repository already has a multi-gpu setting so actually I was just using this code. You can use the multi-gpus by simply...

Model taking lip video as input

Or could you please make it clearer how I can train the model by myself with lip videos as input?

I encountered a KeyError: 'pre_align_cls' while running the preprocess step with the command "python data_gen/tts/bin/pre_align.py". How do I fix it? thanks

Hi, I've met the same problem. Did you fix it?